Denoising
-
JitTrack: Onboard Multi-Object Tracking Against Viewpoint Jitter for Agile UAVs
2026-08-11 05:00:31Yachun Shan, Feitian ZhangAbstract
Multi-object tracking (MOT) onboard agile unmanned aerial vehicles (UAVs) remains challenging due to severe viewpoint jitter induced by camera ego-motion. Rapid attitude changes during flight often lead to significant target displacement across frames, causing inaccurate target association and degraded tracking performance. Existing UAV MOT methods are primarily evaluated on offline benchmarks and seldom address the practical requirements of real-world onboard deployment, including robustness to camera motion and active target following. To address these challenges, we propose JitTrack, an active onboard multi-object tracking framework that accommodates drone dynamics and camera ego-motion. Built upon a query-based transformer tracker, JitTrack introduces semantic refinement to improve the detection of emerging targets, motion-aware query rectification to compensate for target misalignment caused by viewpoint jitter, and a motion-inspired denoising training strategy that simulates camera motion patterns for robust supervision. Furthermore, we develop a perception-planning-control closed-loop tracking pipeline for real-world deployment, enabling collision-free and physically feasible target following on agile UAVs. Extensive experiments on public UAV MOT benchmarks demonstrate consistent improvements over the baseline method, while real-world flight experiments validate the effectiveness and practicality of JitTrack for robust onboard visual tracking under viewpoint jitter.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10485
PDF
-
Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation
2026-08-11 03:39:05Yueting Zhu, Yuehao Song, Kaicheng Zhang, Bao Tang, Shaoyu Chen, Qian Zhang, Wenyu Liu, Xinggang WangAbstract
Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming video diffusion models introduce a fundamental train-inference mismatch: inference follows a specialized denoising order, whereas advanced training strategies typically require diverse noise-level configurations. To address this trade-off between train-inference consistency and training coverage, we reformulate the video diffusion sampling as a frame-indexed stochastic process over noise levels. Within this stochastic process space, we construct a continuous training trajectory along which the sampling schedule progressively evolves from independent sampling to inference-consistent sampling. We further introduce a joint calibration algorithm and a temporal correlative sampling algorithm to ensure trajectory smoothness and cross-frame correlation. Building on these designs, we propose Stream Forcing, a unified training framework for streaming video generation that balances training sufficiency and inference efficiency. Extensive experiments demonstrate that Stream Forcing significantly improves generation quality with a 36.6% FVD improvement on the UCF-101 benchmark. Furthermore, our method facilitates robust zero-shot extrapolation to long-horizon video generation with a 27.9% FVD improvement on the UCF-101 benchmark.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10439
PDF
-
Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning
2026-08-11 03:35:59Yuhang CaoAbstract
Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. For autoregressive models, tool use naturally fits the generation process: the model emits a tool call, waits for the result, and then continues generating. Diffusion language models (dLLMs), however, reason by repeatedly refining many parts of their output in parallel, making this stop-and-resume interaction pattern unnecessarily restrictive. It can force tool decisions before the model's reasoning has stabilized, delay useful observations until a discrete call finishes, and introduce redundant refinement and tool execution, potentially hurting both task accuracy and inference efficiency. We introduce Continuous Interaction Diffusion (CID), a diffusion-native model--runtime architecture that integrates tool interaction into iterative denoising. CID separates a model-read-only fact channel, a thought channel represented by a Typed Cognitive Tensor, and a display channel. Information needs can emerge before a textual or JSON call is fully serialized, allowing perceptual bindings to launch external reads while denoising continues. Returned results are projected into the evolving thought state and can revise earlier cognition and display regions. Persistent bindings reuse static results without repeated external execution and refresh changing sources when needed. CID is designed to expose evidence earlier, overlap tool latency with model computation, reduce duplicate external work, and preserve useful computation after new evidence arrives. We formalize the architecture, runtime, and training objectives, and define an evaluation protocol for task quality and end-to-end efficiency. This first paper focuses on read-only tools and makes no empirical performance claims.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10438
PDF
-
Real-World Cooperative Bimanual Dexterous Grasp of Large Objects from Single-View Observations
2026-08-11 02:24:27Ziming Li, Mingxuan Wu, Jiaqi Zhang, Hongfei Li, Yan Gan, Deqiang Ouyang, Ning WangAbstract
Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation. However, most existing studies focus on sequential manipulation rather than cooperative grasping, and methods addressing such bimanual tasks have largely been limited to simulation. These limitations stem from the difficulty of acquiring full 3D object models and generating physically plausible grasping actions. To fill this gap, we propose a real-world bimanual grasping framework that includes: a multimodal dataset capturing joint angles, visual observations and force signals; a Denoising Diffusion Probabilistic Model (DDPM)-based module that generates joint-level grasp configurations from segmented point clouds; and an execution strategy that integrates motion planning with online grasp refinement to ensure physical stability and feasibility. Our approach enables the synthesis of executable bimanual grasps from single-view inputs, reducing dependence on complete 3D object models and ensuring stable real-world performance. Experiments on a dual-arm robot demonstrate high success rates across unseen objects with varying geometries and poses, and ablation studies confirm the contributions of key components of our system.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10383
PDF
-
ENCORE: Efficient Noise Context-Aware Representation for Low-Dose CT Denoising
2026-08-11 00:57:39Minwoo Yu, N. Robert Bennett, Jongduk Baek, Adam S. WangAbstract
While deep learning-based denoising has become widely adopted in low-dose CT, conventional models use generic architectures designed for natural images, failing to account for non-stationary and spatially correlated CT noise characteristics. To address this, we propose an Efficient Noise COntext-aware REpresentation (ENCORE) framework that explicitly leverages CT noise characteristics and anatomical features. First, we reformulate the noise synthesis procedure based on a realistic noise distribution beyond the conventional Gaussian approximation, establishing a rigorous foundation for training pair generation. Next, we extract local noise power and correlation contexts to guide the denoising process. To fully leverage the potential of noise context, we propose a FlyingConv module, which adaptively changes convolution weights for each local image region. Notably, our approach demonstrates substantial gains in both denoising quality and computational efficiency. Furthermore, manipulating the intensity of the noise context maps at inference time enables zero-shot conditional denoising, allowing for dynamic control over the output image texture. The entire pipeline is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.10343
PDF
-
Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning
2026-08-11 00:02:32Hansen Jin Lillemark, Alex Rojas, Zachary Novack, Runqian Wang, Yilun Du, Yian Ma, Taylor Berg-Kirkpatrick, Rose YuAbstract
Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling. This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample, improving video quality and consistency on challenging autoregressive video generation benchmarks. Extensive analysis elucidates exactly how removing the noise level conditioning enables EqF's data-dependent inference properties to surpass the performance of standard noise level-conditional denoising video methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14706
PDF
-
TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration
2026-08-10 22:43:06Linlian Jiang, Yuchen Xi, Sadman Rakib Pinon, Ruigang Yang, Yang Wang, Xinxin ZuoAbstract
We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting a diffusion prior to sparse-view 3D Gaussian Splatting (3DGS) restoration. Rather than pursuing increasingly sophisticated restoration architectures, we identify a more fundamental limitation shared by existing diffusion-based approaches: supervision at independently noised states does not cover those reached during inference. In sparse-view 3DGS, under-constrained geometry biases denoising from the outset, and the resulting deviations compound along the rollout. TRACE-GS instead performs on-policy trajectory distillation: a teacher conditioned on richer geometry from additional training views supplies targets along the sparse-view student's own rollout, aligning denoising directions and cross-view responses at each visited state. This training-only geometry places TRACE-GS in the learning using privileged information (LUPI) setting. At deployment, only the sparse-view student is retained, and its restored renderings serve as pseudo-observations for 3DGS refinement. To the best of our knowledge, TRACE-GS is the first to derive on-policy supervision from privileged geometry for sparse-view 3DGS restoration, achieving consistent gains and strong generalization across datasets and sparse-view settings.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10286
PDF
-
DoseBridge: Denoising Diffusion Bridge Model for Dose Prediction in Lung Intensity-Modulated Proton Therapy
2026-08-10 19:43:10Zerun Zhang, Xiaoda Cong, Xiangkun Xu, Peter Y. Chen, Xuanfeng DingAbstract
Most radiotherapy dose-prediction models use only CT images and anatomical structures, although intensity-modulated proton therapy (IMPT) dose also depends strongly on beam geometry and available clinical datasets are often small. We present DoseBridge, a denoising diffusion bridge model that uses the patient CT as a structured bridge endpoint and encodes plan-specific beam geometry in a spatially aligned beam mask. Multiscale fusion combines CT, target, organ-at-risk, and beam-mask representations with 1.95% additional parameters. DoseBridge was retrospectively evaluated on single-institution CT images and treatment plans from 52 patients with advanced-stage lung cancer treated with 60 Gy in 30 fractions; 42 cases were used for training and 10 for testing. Performance was assessed using image-similarity, dose-volume, and Lyman-Kutcher-Burman normal-tissue complication probability (NTCP) metrics and compared with two deep-learning models. On the test cohort, DoseBridge achieved a mean absolute error of 4.170 Gy, peak signal-to-noise ratio of 23.06 dB, and structural similarity index of 0.798, outperforming both comparison models on these metrics. Clinical target volume D95 differed from the reference dose by 0.62 +/- 1.6 Gy; signed organ-at-risk mean-dose differences ranged from -0.32 to 0.24 Gy, and NTCP differences were -0.40 +/- 2.2 and 0.52 +/- 3.4 percentage points for acute esophagitis and radiation pneumonitis, respectively. Changing only the beam mask redirected predicted low-dose entrance regions while preserving the high-dose target region. To our knowledge, DoseBridge is the first denoising diffusion bridge model for radiotherapy dose prediction. These results support its feasibility as a beam-aware planning prior for lung IMPT, pending evaluation in larger external cohorts.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10173
PDF
-
Training Set Synthesis for Bioacoustic Denoising: A Case Study With Mice
2026-08-10 17:53:14Reyhaneh Abbasi, Peter Balazs, Vincent Lostanlen, Clara Hollomey, Dustin J. Penn, Sarah M. Zala, Nicki HolighausAbstract
Bioacoustic recordings are often degraded by ambient noise, which complicates the analysis of weak or noise-overlapped vocalizations. Convolutional neural networks, particularly U-Net architectures, have shown a strong denoising performance in speech and music processing. However, their direct application to bioacoustic signals is limited by the scarcity of clean training data. To address this issue, we propose a training set synthesis approach and develop a supervised denoising model that predicts a complex ratio mask in the time-frequency domain. The model leverages ridges, or frequency contours, that represent the fundamental frequency together with one or more harmonic partial components of vocalizations. These ridges are used both for the synthesis of training sets and to design a loss function that assigns higher weights to the ridge regions (ridge-guided loss function). This weighting step helps the network better preserve vocalization details during denoising. As a case study, we evaluate our approach using ultrasonic vocalizations (USVs) recordings of house mice, which are widely studied in behavioral biology and neuroscience. In actual field recordings, the proposed method enhances fundamental and harmonic partial ridge tracking compared to our previous signal-processing approach. In addition, a classifier trained on denoised data improves USV classification on out-of-sample, noisy recordings from wild and domesticated mice compared to classifiers trained on noisy recordings. Our proposed method also substantially improves the scale-invariant signal-to-distortion ratio on synthetic testing data across a wide range of input signal-to-noise ratios. Although we focus on USVs, the proposed approach should be broadly applicable to other bioacoustic signals with trackable ridges, and thus enables ridgebased training set synthesis and denoising.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10054
PDF
-
Second-Order Muon Done Right: A Principled Marriage of Spectral Geometry and Curvature
Abstract
Muon's polar update is exact for an unweighted spectral geometry. We introduce GO-MUON, which uses a matched data-dependent geometry and reuses it across several optimization steps. Conditioned on any positive-definite left and right maps, its raw update exactly solves the corresponding weighted spectral oracle; this statement is independent of how the maps are estimated or how recently they were refreshed. For softmax cross-entropy, we quantify when the observed-label backward factor approaches the model Fisher and generalized Gauss--Newton factor. We also show that four-step refresh nearly preserves the tracking delay of slowly changing geometry while increasing stationary factor noise, making lazy geometry a compute--statistics tradeoff rather than a denoising mechanism.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09763
PDF
-
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
2026-08-10 15:30:38Qu Tang, Benhui Zhuang, Bo Yuan, Xue Yu, Longteng Guo, Junlan FengAbstract
Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes evolve as a task unfolds. Recently emerging world-action models (WAMs) leverage pretrained video world models to capture spatiotemporal evolution, yet retaining future generation or a large video backbone in the control loop substantially increases inference cost. We introduce World Tokens, an embodied policy architecture built around a World Adapter that bridges visual-language understanding, world-dynamics modeling, and action generation. It uses world modeling during training to enhance the action policy while preserving efficient deployment. Specifically, the World Adapter transforms VLM features into a fixed set of world tokens, which condition a jointly fine-tuned future-video denoiser and simultaneously serve as the action expert's sole visual-language context. This shared conditioning allows gradients from future-video denoising to directly shape the representation used for action prediction, while exclusive routing prevents the policy from bypassing that representation. At deployment, the world-model branch is removed, leaving only the VLM, World Adapter, and action expert, with no online video-model inference. With a 2B backbone and no embodied action pretraining, World Tokens is highly competitive on LIBERO, attains the best reported averages on SIMPLER, substantially improves real-world R1 Pro success over a matched action-only baseline, and generates each action chunk at VLA-level latency.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09730
PDF
-
MPISuperRes-PnP: A Super-Resolution Zero-Shot Plug-and-Play Reconstruction Algorithm for Magnetic Particle Imaging
2026-08-10 14:47:23Vladyslav Gapyak, Thomas M\"arz, Andreas WeinmannAbstract
Magnetic Particle Imaging (MPI) is an emerging medical imaging modality. MPI is based on the non-linear response of magnetic nanoparticles to an applied magnetic field and avoids ionizing radiation. The measured signal is the voltage induced in receive coils by the particles' response. Reconstructing the particle concentration from the signal constitutes the imaging task. Even using state-of-the-art measurement-based reconstruction, the associated spatial grid is very coarse, hence super-resolution (SR) techniques are important. In this work, we propose an approach for SR in MPI inspired by energy minimization. Different methods have been proposed for SR in MPI, ranging from upscaling of the associated system matrix to interpolation of the reconstruction. Here we incorporate SR into the reconstruction task via an energy minimization formulation. Following the plug-and-play approach to energy minimization we derive a splitting scheme and a SR method for MPI where the arising Gaussian denoising task is treated with a pre-trained learned Gaussian denoiser in a zero-shot fashion. This way, we incorporate benefits of deep learning without training and avoid the need of training data. Further, we provide a quantitative and qualitative evaluation of the proposed method. Hyper-parameter are selected via an extended parameter search. The found parameters are applied for reconstruction on real data. We show the applicability of our method on synthetic and on real data (MPIData: EquilibriumModelWithAnisotropy and 2D-OpenMPI Data). The proposed method employs a deep-learning denoiser without training -- thus it does not require presently scarcely available MPI training data. The denoiser behaves conservatively, i.e., no hallucination artifacts were observed. The SR approach is generic such that it can be applied in future MPI contexts involving different regularizers or different imaging tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09672
PDF
-
You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows
2026-08-10 13:15:09Jonas Leo Mueller, Sebastian Hoefler, Dario Zanca, Naga Venkata Sai Jitin Jami, Thomas Altstidl, Bjoern M. EskofierAbstract
Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Yet existing radar methods remain deterministic, collapsing this ambiguity into a single estimate. Diffusion-based alternatives can model multi-hypothesis distributions but require costly sequential denoising for each distribution sample and lack calibrated uncertainty. We propose Multi-Hypothesis Normalizing Flow Pose Generator (MH-NFPG), which models pose distributions from radar point clouds using a conditional normalizing flow. Specifically, we combine a spatiotemporal transformer backbone with a normalizing flow that transforms a Laplace base distribution into an expressive posterior, generated in parallel through a single forward pass. Leveraging this efficiency, we outperform diffusion-based alternatives in calibration across three radar benchmarks (MM-Fi, mmRadPose, mRI), improve pose accuracy on two, and match it on the third, while achieving over 20x faster inference for applications and reducing calibration error by up to 85%. We find that calibration degrades substantially for diffusion models, whereas our flow-based approach maintains reliable coverage, also in cross-environment settings. These results demonstrate normalizing flows as a practical alternative to diffusion models for real-time, uncertainty-aware radar pose estimation. Our code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09579
PDF
-
DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation
2026-08-10 12:35:39Lingming Su (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Wanglong Lu (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China, AI Analytics Team, Nasdaq, St. John's, Canada), Tao Wang (vivo Mobile Communication Co., Ltd, Shanghai, China), Kaihao Zhang (College of Engineering and Computer Science, The Australian National University, Canberra, Australia), Nan Zhang (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Liyan An (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China), Hanli Zhao (College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China)Abstract
High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degradations, they often struggle with training multiple degradation-specific models, reliance on manual task-specific prompts, or cross-task data pairing. To address these limitations, we propose DocPure, a prompt-free unified framework that achieves degradation-aware document restoration. We design a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs. The model is prompt-free at inference, and degradation labels are only used as auxiliary supervision for the routing regularization during training. Furthermore, we introduce a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics. Within the structure-guided wavelet interaction mechanism, a cross-frequency adaptive modulation utilizes low-frequency sub-bands to modulate high-frequency recovery, ensuring structural consistency. Extensive experiments demonstrate that DocPure achieves strong performance compared with state-of-the-art methods across various tasks, including deblurring, denoising, compression artifact reduction, and deshadowing.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09536
PDF
-
Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance
2026-08-10 11:48:22Chunxiao Liu, Wei Liu, Anbin Xiong, Erli MengAbstract
All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model. Recent works have achieved remarkable progress by learning degradation-adaptive prompts or network architectures. However, these methods typically apply a uniform restoration strategy across the entire image, neglecting the fact that different regions may suffer from distinct degradation types and varying degrees of severity. In contrast, we propose to perform restoration at the pixel level, thereby enabling more fine-grained and precise control over the restoration process. Specifically, we present MGN-AIR, a novel pixel-level restoration framework for all-in-one image restoration. Our approach first learns to estimate a pixel-level visual prompt. Then, it leverages both textual and visual prompts to provide global and local degradation cues, guiding the model on where to look and how to restore at each pixel. We conduct extensive experiments on multiple all-in-one image restoration benchmarks, covering a wide range of tasks including denoising, deraining, deblurring, dehazing, desnowing, and low-light enhancement. Experimental results demonstrate that our proposed method consistently and significantly outperforms existing approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09482
PDF
-
DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging
2026-08-10 11:20:35Jiayang Zhang, Ji Guo, Jiachen Li, Wenshu Fan, Wenbo JiangAbstract
Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitigation is difficult without knowing the compromised source, trigger, or target, and broad sanitization may degrade image quality. We introduce DiffSafeMerge (DSM), which uses a small unlabeled clean set and fixed, attack-agnostic stress probes to score source blocks, shrink suspicious contributions toward a trusted reference, and select attenuation under a clean denoising-loss budget. We evaluate four attacks, two datasets, and 21 target conditions. Intended merging already has zero worst-target ASR in 10 of 14 source cases; DSM preserves these outcomes and records no target match in the remaining four over three seeds, including three with baseline ASR of 48--100\%. Among methods with zero worst-target ASR on both datasets, DSM obtains the lowest case-averaged FID in the matched seed-0 comparison.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09445
PDF
-
Reducing Pretraining-Generation Mismatch in Diffusion Language Models
2026-08-10 10:52:20Xiaocheng Lu, Huabin Liu, Song Guo, Jianguo LiAbstract
Autoregressive language models align training and use: generation conditions on a clean prompt, and training predicts future tokens from clean left context. Diffusion language models offer parallel denoising, but native dLLM pretraining can randomly corrupt prompt and continuation tokens together, weakening the clean-prefix interface needed for prompt-conditioned generation. We identify this mismatch for prompt continuation and propose PCD (Prefix-Conditioned Diffusion), a pretraining objective that combines AR prefix supervision with no-shift suffix denoising. At the training-objective level, PCD changes the attention mask, corruption mask, and label construction in continued pretraining; it does not require an autoregressive decoder, verifier, or new inference mode. By supervising the clean-prefix side autoregressively and applying diffusion only to the unknown continuation, PCD makes the local training interface resemble how block-diffusion models are queried at evaluation time. We further separate intra-sample prefix conditioning from inter-sample objective mixing, allowing us to identify the local alignment signal separately from the optional batch-level mixing knob. Across LLaDA2-Mini and Qwen-1.7B backbones, PCD consistently improves over same-family native dLLM stable baselines, reaching a 4.2% relative gain on the main LLaDA2-Mini six-benchmark average (+2.56 points) and a 14.2% relative gain in the primary Qwen mechanism comparison (+4.86 points). These results suggest that aligning the pretraining context distribution with prompt-conditioned generation can recover a measurable part of the dLLM continuation gap without changing inference.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09424
PDF
-
MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution
2026-08-10 10:33:18Axi Niu, Jiawei Kou, Kang Zhang, Qingsen Yan, Jinqiu Sun, Yanning ZhangAbstract
Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods reduce inference time but depend on expensive pretrained teachers, whereas CTMSR avoids distillation through PF-ODE consistency training yet does not explicitly model the restoration dynamics from low-resolution (LR) inputs to high-resolution (HR) images. We propose MeanSR, a one-step perceptual SR method that learns an LR-conditioned average velocity field to directly capture the finite-time transition from degraded or noisy inputs to plausible HR outputs. We further reformulate distribution trajectory matching for average-velocity generation and introduce a Stage-Aware Temporal Sampling strategy to improve trajectory learning. Experiments on synthetic and real-world benchmarks show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency. MeanSR also reconstructs sharper structures and more realistic textures with fewer perceptual artifacts.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09405
PDF
-
Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation
2026-08-10 09:35:36Zhe Li, Honghao Qiao, Zhixin Xu, Qijie Wang, Bo Peng, Dawei LiAbstract
RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09355
PDF
-
Diffusion Image Editing via Asynchronous Token Decoding
2026-08-10 09:02:13Yang Shi, Liangsi Lu, Minzhe Guo, Yifeng Xie, Yanhui Chen, Jingchao Wang, Xuhang ChenAbstract
Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, naïvely switching the text condition during sampling often causes global drift, as denoising dynamics propagate changes across tokens and can disrupt unedited regions. To address this issue, we propose \textbf{A}synchronous \textbf{T}oken \textbf{D}ecoding \textbf{Edit} (ATDEdit), an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix and enables token-indexed condition switching with differentiated update policies. Instead of applying synchronous target-conditioned updates to all tokens, ATDEdit estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set. It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values; these operations promote background preservation but do not constitute a pixel-level invariance guarantee. This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning. On PIE-Bench, ATDEdit achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS, while retaining competitive semantic alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09322
PDF
