arXiv_CV
-
Hierarchical Denoising For Multi-Step Visual Reasoning
2026-07-16 17:59:57Zezhong Qian, Xiaowei Chi, Chak-Wing Mak, Tianze Zhou, Ruibin Yuan, Yuhan Rui, Hengzhe Sun, Zhuoqun Wu, Yuming Li, Siyuan Qian, Sirui Han, Shanghang ZhangAbstract
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR organizes video latents into a tree-structured hierarchy, enabling coarse-to-fine reasoning before streaming output. Coarse denoising layers preserve uncertain hypotheses for global planning, while finer layers progressively refine them into concrete visual states. A sparse hierarchical attention pattern (SHAP) further reduces temporal attention costs. We introduce a level-stratified multi-step video reasoning benchmark with out-of-distribution cases, covering six tasks: maze navigation, Tower of Hanoi, one-line drawing, sliding puzzle, Sokoban, and water pouring. Compared with streaming autoregressive diffusion baselines, HDR improves success from 34.22 to 60.29 (76.2% relative gain) and increases average progress from 76.00 to 89.56, demonstrating more consistent reasoning trajectories. HDR maintains low-latency streaming at 0.70 seconds per latent, achieving 54.2 times faster inference than bidirectional diffusion. It also retains 82.9% of full-data performance with only 2% training data, compared with 52.0% for bidirectional diffusion. Real-world robot experiments further demonstrate HDR's potential for physical interaction and world modeling. Project demo: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15278
PDF
-
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
2026-07-16 17:59:02Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo, Tianyu PangAbstract
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow remains underexplored. DiffusionNFT optimizes instantaneous velocities, whereas MeanFlow samples with average velocities. To bridge this gap, we introduce MeanFlowNFT. Inspired by the MeanFlow identity, which bridges average and instantaneous velocities, we construct an induced instantaneous-velocity predictor. We apply the DiffusionNFT objective to this predictor, making reward optimization well-defined for MeanFlow. Sampling remains based on the average velocity, preserving MeanFlow's fast few-step generation. We further prove that MeanFlowNFT inherits DiffusionNFT's strict policy-improvement guarantee. Experiments on image and video generation show that MeanFlowNFT consistently improves baselines. Moreover, it outperforms prior state-of-the-art RL-tuned few-step generators on most metrics ($6$ of $8$ on SD3.5-M), and can even surpass multi-step RL-tuned diffusion while using only a few sampling steps. For instance, on Wan 2.1, $4$-step MeanFlowNFT reaches a VBench score of $84.33$, surpassing $50$-step LongCat-Video RL ($82.57$).
Abstract (translated)
URL
https://arxiv.org/abs/2607.15273
PDF
-
Online Neural Space Time Memory for Dynamic Novel View Synthesis
2026-07-16 17:58:18Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, Ali Behrouz, Yuan Deng, Stephen Lombardi, Steven M. Seitz, Xuan LuoAbstract
Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism, standard models mandate gradient-based memory updates at every frame to adapt to the changing motion in dynamic scenes. The computational cost of heavy memory updates precludes real-time application and can lead to instability over long contexts. Given that memory updates are more demanding than memory application and video content is largely redundant, we propose to decouple the frequencies of these two processes. Our approach performs periodic memory updates while applying the memory on a per-frame basis, using cross-view attention to manage deformations between the prior memory state and the current frame. To lock in the historical context, we introduce two critical mechanisms: an auxiliary Memory Loss that forces persistent internalization of the scene, and a Memory Caching strategy that regularizes active weights against catastrophic drift. Our method demonstrates real-time, state-of-the-art performance on scenes with dynamic human motion as well as minute-scale online memorization.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15271
PDF
-
Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography
2026-07-16 17:56:56Guang Yang, Wentian Xu, Siyu Wang, Betty Raman, Lei Li, Vicente GrauAbstract
Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptors or densely supervised estimation, but the need for extensive annotation limits applicability. Foundation models have recently improved vision-based Echo analysis; however, most methods operate on single views and segment-level localization remains unreliable under view-dependent ambiguity, especially in apical views. To address this, we propose MCF-Net, a novel motion-guided multi-view fusion framework that fuses myocardial motion cues with foundation model representations to localize infarction. Visual features are extracted using EchoPrime, a pretrained Echo foundation model shared across dual views. Cardiac motion is modeled with extremely sparse supervision: a single annotated template frame is transferred across videos to initialize point tracking, avoiding dense labels. Motion-derived segment-aware soft masks provide coarse spatial priors that selectively enhance features for challenging myocardial segments. A motion-conditioned fusion mechanism then integrates motion and vision across views, refining predictions without overriding strong appearance cues. On segment-level MI localization, MCF-Net achieves 72.4\% F1 and 84.9\% accuracy, outperforming state-of-the-art motion-only, vision-only, and fusion baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15268
PDF
-
HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning
2026-07-16 17:50:03Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne HsuAbstract
Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically investigate this issue, we first design two quantitative metrics, Bias Intensity (BI) and Bias Harmfulness (BH), to characterize the impact of landmarks exerted on model reasoning, and establish a comprehensive benchmark, LandmarkBias-3K. To mitigate landmark bias, we further propose an evidence-driven reasoning framework, HoloGeo, to improve the reliability of geo-localization. HoloGeo is supported by a high-quality dataset, BF-30k, annotated with structured multi-evidence bias-free reasoning chains. By incorporating multi-dimensional rewards, HoloGeo explicitly encourages balanced attention over diverse visual cues and achieves evidence-driven joint reasoning. Extensive experiments demonstrate that HoloGeo not only maintains excellent performance on IM2GPS3K and YFCC4k but also significantly outperforms existing open-source VLMs on LandmarkBias-3K, validating its effectiveness for robust geospatial reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15255
PDF
-
ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
2026-07-16 17:45:13Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho, Pai Chet Ng, Xiaoxiao Miao, Konstantinos N. PlataniotisAbstract
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when perturbations are transferred from convolutional surrogates to transformer-based targets. To address these limitations, this paper introduces ARMOR++, a robust multi-agent framework designed for high-transferability deepfake evasion. The framework leverages the Qwen2.5-VL Vision-Language Model (VLM) to supply spatial semantic priors, while the Qwen3 Large Language Model (LLM) orchestrates primitive selection, adaptive hyperparameter reparameterization, and entropy-regularized perturbation mixing. By integrating five complementary primitives, spanning dense optimization, saliency-based methods, spatial transformations, frequency-domain perturbations, and block-structured modifications, ARMOR++ effectively targets heterogeneous inductive biases. Rigorous evaluation on the AADD-2025 benchmark demonstrates that ARMOR++ significantly outperforms existing agentic and non-agentic baselines across both low- and high-quality image regimes. Statistical analysis confirms a substantial gain in blind-target Attack Success Rate (ASR) over the state-of-the-art agentic baseline, with further performance advantages evidenced against non-agentic benchmarks and under robust defensive configurations. These findings highlight a significant residual reliability gap in current deepfake detector deployments and demonstrate the efficacy of agentic orchestration in identifying latent vulnerabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15246
PDF
-
Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA
2026-07-16 17:38:19Sushant Gautam, Vajira Thambawita, Michael A. Riegler, P{\aa}l Halvorsen, Steven A. HicksAbstract
Healthcare multimodal AI must combine visual and textual evidence while remaining reliable and interpretable. Using MediaEval Medico 2025 as a retrospective GI endoscopy case study, we analyze design choices across nine documented systems for question answering and explanation quality. Parameter-efficient adaptation of pretrained backbones provides strong challenge performance, but answer-level gains do not consistently translate into faithful and complete clinical reasoning. Methods enforcing structured reasoning and explicit grounding show more reliable behavior across heterogeneous question types, although the evidence is correlational rather than ablation-based. These results motivate evaluation beyond lexical overlap, standardized evidence-linked explanations, leakage-aware data governance, and lightweight robustness and calibration checks. The findings support trustworthy multimodal healthcare AI based on data fusion, explainability, and resilient evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15241
PDF
-
CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift
2026-07-16 17:32:26Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi ZhouAbstract
Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by exhausting predefined possibilities through simulated shifts or pseudo-supervision. Such strategies struggle in the open-ended and unpredictable real world, where distribution shifts are effectively infinite. To address this challenge, we adopt the "Rank Stability of Positive Regions" as a working assumption under distribution shift, and use it to derive robust spatial hints for source-only segmentation. Guided by this assumption, we propose CRISP, a model-agnostic framework that, unlike deployment-time adaptation, requires no test-time parameter updates and no target-domain data--a target-free, plug-in refinement framework that segments with frozen weights. Rather than using ranking to directly output masks, CRISP exploits the stability of probability rankings under distribution shift to derive robust spatial priors. Via latent feature perturbation, perturbation-invariant high-grade regions define a high-precision (HP) core, while voxels that remain potentially foreground under at least one perturbation define a high-recall (HR) support; these dual priors are then recursively refined under perturbation. We then design an iterative training framework that progressively squeezes HP and HR toward the final segmentation. Extensive evaluations on multi-center cardiac MRI and CT-based lung vessel segmentation demonstrate CRISP's superior robustness, significantly outperforming state-of-the-art methods with striking HD95 reductions of up to 0.14 (7.0% improvement), 1.90 (13.1% improvement), and 8.39 (38.9% improvement) pixels across multi-center, demographic, and modality shifts, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15231
PDF
-
Divergent Gaze Patterns in Artistic Viewing: Spatial and Temporal Signatures of Attention Across Autistic Individuals, Artists, and Neurotypical Observers
2026-07-16 17:29:18Mohammed Amine Kerkouri, Daphn\'e Senggaran, Renaud Jusiak, Oc\'eane Lehmann, Marouane Tliba, Claire Wardak, Emmanuelle Houy-Durand, Shasha Morel-Kohlmeyer, Aladine Chetouani, Nadia Aguillon-HernandezAbstract
How different populations visually explore artworks bears on cognitive science and on accessibility design, yet most eye-tracking work in autism has used social scenes rather than art, and has analysed where the eyes land while ignoring when and in what order. We present a comparative free-viewing study across three groups, autistic adults (ASD), trained artists, and neurotypical observers, who each viewed 30 paintings for 15s. We introduce a directed, metric-grounded framework that compares groups along two complementary axes: a spatial axis, in which one group's fixation-density map predicts another's fixations under six saliency metrics (AUC-Judd, NSS, CC, SIM, KL, Information Gain); and a temporal axis, in which individual scanpaths are compared with MultiMatch, ScanMatch, a foveal-disc IoU score (FDISS), and dynamic time warping (DTW). Fixations are extracted uniformly for all groups with a dispersion-threshold algorithm. Three results converge. (i)Artists and neurotypicals are almost indistinguishable in both space (density-map correlation CC=0.96) and time (they form the most alignable scanpath pair), whereas ASD gaze diverges from both. (ii)ASD attention is dissociated: it matches artists' wide spatial exploration (dispersion, explored area) but carries a distinct temporal signature, shorter fixations, less dwell, and the most idiosyncratic (least self-consistent) scanpaths of any group. (iii)ASD gaze is not selectively artist-like on any metric; if anything it is marginally closer to neurotypical. Together these findings indicate that autistic viewing of art is a distinct, group-specific attentional profile in both space and time, and they motivate population-conditioned models of aesthetic attention. We release all analysis code and per-stimulus results.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15227
PDF
-
Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification
2026-07-16 17:22:51Moyao Tian, Shijia Liu, Yan Yang, Xin Yuan, Minshi Chen, Wei Wang, Xiao WangAbstract
Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framework that transforms open-loop association into a self-correcting closed-loop system. Structurally, we introduce Fine-grained Structural Decoupling (FSD) to extract discriminative body-part primitives as reliable spatial anchors, complementing ambiguous holistic silhouettes with spatially consistent structural details. Semantically, we design a Closed-loop Semantic Calibration (CSC) mechanism that reconstructs shared semantic prototypes at each epoch and feeds them back into the training loop, effectively filtering pseudo-label noise before the next clustering cycle. Through the reciprocal interaction between structural and semantic learning, SSRL achieves robust cross-modal representation. Extensive experiments demonstrate the competitive performance of SSRL against state-of-the-art USVI-ReID methods on both SYSU-MM01 and RegDB, notably surpassing several supervised counterparts on RegDB.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15220
PDF
-
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
2026-07-16 17:12:58Ziren Gong, Xiaohan Li, Fabio Tosi, Ninghui Xu, Stefano Mattoccia, Jianfei Cai, Matteo PoggiAbstract
This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on a feed-forward model from the 3R family to process RGB videos and regress local point maps, and on a merging model, MAGMA, that combines local maps at both intra-agent and inter-agent levels to obtain the final global point map. Furthermore, MAGiSt3R performs pose graph optimization to mitigate cumulative camera drift occurring along the feed-forward pipeline. We evaluate MAGiSt3R on both synthetic and real-world datasets, demonstrating its superior reconstruction and camera tracking accuracy compared to state-of-the-art approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15211
PDF
-
Ray-based phase error correction for miniaturized DOE projector-based FPP under single-directional hyperbolic projection
Abstract
Fringe Projection Profilometry (FPP) systems using miniaturized DOE pro-jectors often suffer from severe phase artifacts due to nonlinear projection characteristics and limited pattern controllability. We propose a ray-based phase error correction framework that models phase artifacts along projection rays from the projector pinhole, incorporating projector geometry without re-lying on image-domain processing or neighboring pixels. A projector pinhole estimation method based on a single-directional hyperbolic fringe pattern is introduced, through which projector geometry can be recovered without stereo calibration. In addition, a data-efficient strategy constructs the re-finement model from a single calibration pose. Experiments on miniaturized DOE projector-based FPP systems demonstrate significant improvements in reconstruction accuracy under nonlinear projection conditions, confirming the robustness and physical consistency of the proposed approach.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15139
PDF
-
DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification
2026-07-16 15:37:32Pengkun Wang, Weijia Cao, Ning Wang, Xiaofei YangAbstract
Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI classifiers usually construct graph topology from spatial proximity, superpixel connectivity, or learned feature affinity. However, the spectral physical prior carried by contiguous bands has limited influence on topology estimation and message propagation. This paper presents DAPGNet, a dynamic adaptive physics-guided graph diffusion network that injects a structure-constrained physical prior into relation-level graph learning. DAPGNet first encodes contiguous spectral responses into node-wise multiscale physical-prior representations. A two-stage graph constructor then combines spectral-spatial affinity, physical-prior consistency, and spatial distance to form a physical-prior-aware sparse topology. During graph diffusion, learned edge weights are transformed into additive attention biases, while a physical gate performs node-wise and feature-wise interpolation between graph-aggregated features and projected physical-prior features. Cross-scale fusion integrates node states from different diffusion depths, and the network is optimized with main classification, auxiliary supervision, and second-order spectral smoothness regularization. Experiments on Indian Pines, WHU-Hi-LongKou, Houston2013, and Houston2018 show that DAPGNet achieves the best OA, AA, and Kappa among representative CNN-, Transformer-, Mamba-, and graph-based baselines. It improves AA over the strongest competing method by 3.64 to 7.31 percentage points across the four datasets. Ablation and sensitivity analyses further support the complementary effects of physical-prior extraction, prior-aware topology construction, physics-gated propagation, and spectral smoothness regularization.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15128
PDF
-
QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration
2026-07-16 15:10:00Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian, Zhen Wu, Guangwen Peng, Zhiyuan Li, Ding Ding, Dian Shen, Fang DongAbstract
All-in-one image restoration aims to recover clean images degraded by multiple corruption types using a single unified model. Existing methods typically rely on image-level prompts or shared guidance to handle diverse degradations. However, such a paradigm becomes inadequate when degradations are spatially heterogeneous or even coexist in mixed forms within a single image. Yet spatially adaptive guidance alone is not sufficient, since accurate restoration also requires each spatial query to reliably aggregate complementary information from local neighborhoods and global contexts. To this end, we propose QuReC, a unified framework for all-in-one image restoration. QuReC consists of a Degradation-Guided Query Reconstruction Module (DQRM) and a Local-Global Response Calibration Module (LGRCM). Specifically, DQRM matches each spatial query against a degradation prototype space to reconstruct a query-specific degradation-aware representation, thereby providing fine-grained spatially adaptive restoration guidance. To further stabilize this query-wise matching process, we introduce a weakly supervised prototype matching learning strategy to improve optimization stability and degradation semantic consistency. Meanwhile, LGRCM performs local-global dual-branch aggregation and calibrates the aggregated responses with learnable priors, improving the reliability of feature aggregation and the coordination between local detail modeling and global context modeling. Extensive experiments demonstrate that QuReC achieves superior performance on multiple all-in-one image restoration benchmarks. The code is released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15097
PDF
-
AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
2026-07-16 15:07:23Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao LiuAbstract
Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every retrieval direction to the same stability-plasticity trade-off. We propose AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints. For each aligned parameter tensor identified by its checkpoint key, AlphaWiSE fits one scalar interpolation coefficient shared by all tensor entries. The coefficients are fitted on a smaller exemplar memory and used to materialize one interpolated checkpoint. The deployed model has the same architecture and parameter count as either source checkpoint, which does not require additional inference time. Extensive experiments on audio-image-text retrieval show consistent improvements over strong continual-learning baselines across multiple retrieval directions and evaluation metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15094
PDF
-
Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
2026-07-16 14:57:25\"Unsal \"Ozt\"urk, S\'ebastien MarcelAbstract
Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form clusters with different geometric properties. In this paper, we quantify the magnitude of this difference and what training-time factors control it. We compute four statistics based on cluster geometry across 180 face recognition models in a factorial design over IResNet backbone size, loss head, training duration, and the number of training identities, and evaluate each configuration on nine benchmarks. Our results indicate that the number of training identities has the largest effect on member/non-member separability, while backbone and loss head contribute far less, and that, on a same-domain held-out reference, the geometric membership signal decreases monotonically as more identities are added to training. We provide an analysis of cross-domain (pose, age, quality, ethnicity) non-member benchmarks and report that these inflate the apparent membership signal. Finally, we fuse all four statistics with a learned classifier to reveal additional membership information beyond the best individual statistic.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15084
PDF
-
ESAR: Event-Based Synthetic Aperture Reconstruction
2026-07-16 14:45:18Harbir Antil, Daniel Blauvelt, David SayreAbstract
Event cameras report asynchronous polarity events when changes in log--radiance exceed a fixed contrast threshold, producing signed temporal contrast measurements rather than conventional image frames. We formulate monocular event-based imaging as a synthetic-aperture inverse problem for a static ground-domain log--radiance field $\theta \in \mathbb{R}^{N_g}$. Instead of reconstructing a latent pixel-time volume $v \in \mathbb{R}^{N_pN_t}$, we impose the geometric relation $v=P\theta$, where $P$ maps the fixed scene into motion-dependent latent views. Aggregating events over finite time intervals gives the linearized model \[ AP\theta = b+\eta, \] where $A$ is a temporal differencing operator, $b$ contains signed binned event counts, and $\eta$ represents measurement and modeling errors. This decomposition exposes a synthetic-aperture structure: under near-nadir motion, successive projections are approximately shifted views of a common scene, while the composite operator $AP$ remains ill-conditioned because it combines spatial averaging with temporal differencing. We therefore use regularized inversion to recover $\theta$. Numerical experiments on simulated data and real near-nadir Falcon Neuro event data show that the proposed $\theta$-based formulation recovers coherent large-scale spatial structure, relative to dynamic latent-image and learned event-reconstruction baselines, while suppressing fine-scale texture.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15073
PDF
-
DriftWorld: Fast World Modeling through Drifting
2026-07-16 14:37:43Susie Lu, Haonan Chen, Weirui Ye, Yilun DuAbstract
Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action search at inference time. We introduce DriftWorld, an action-conditioned world model based on drifting generative models. Rather than denoising iteratively at inference, DriftWorld learns an action-conditioned drift during training, allowing it to generate future frames from the current observation and a candidate action sequence in a single forward pass at 30+ fps, which is 17x faster on average than diffusion based baselines. We evaluate DriftWorld on standard vision-based robotic manipulation benchmarks, including Bridge-V2, RT-1, Language Table, Push-T, and Robomimic. By producing rollouts that are both accurate and fast, DriftWorld achieves state-of-the-art decision-making performance with far less inference time than diffusion-based world model baselines. Beyond online control, DriftWorld can also serve as an offline simulator for ranking real-world robot policies, with rollout-based scores correlating with ground truth at up to 0.99. These results show that drifting models are a strong fit for robot world modeling, where fast, high-quality imagination directly supports planning and policy evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15065
PDF
-
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
2026-07-16 14:32:34Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera, Holger Voos, Jose Luis Sanchez-LopezAbstract
CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a weakly-supervised framework for zero-shot CAD alignment with two key contributions. First, SUFLECA scales up geometry-grounded feature learning from pretrained visual representations through Normalized Object Coordinates (NOCs) supervision on 674K images spanning 12 real and synthetic datasets, learning compact geometry-aware features that generalize across domains. Second, we propose a geometrically consistent matching algorithm that establishes reliable one-to-one CAD-to-image correspondences. Together, these contributions enable accurate, sub-second alignment per object instance without iterative pose refinement. On ScanNet25k, SUFLECA achieves 33.4%/42.3% category/instance accuracy, outperforming, with a smaller computational footprint, the strongest zero-shot baseline by 10.3/12.2 percentage points and, for the first time on this benchmark, even surpassing fully supervised methods. Code is available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.15058
PDF
-
Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
2026-07-16 14:31:16Xiao Lin, Xiaohu Huang, Kai HanAbstract
Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when integrating diverse foundation models into MLLMs, different models provide complementary spatial priors that benefit different tasks. Motivated by this, we propose $\textbf{ViPS}$, a novel multi-model prior framework designed to fully unleash the potential of incorporating multiple $\textbf{Vi}$sual $\textbf{P}$riors from diverse models into MLLMs for $\textbf{S}$patial understanding. Specifically, ViPS introduces an Efficient Prior Proxy to generate multiple foundational priors with minimal inference overhead, and a Dynamic Prior Fusion mechanism to achieve harmonious and context-aware prior fusion and injection from the prior proxies. Extensive experiments demonstrate that ViPS successfully harmonizes diverse visual priors, establishing new state-of-the-art performance across multiple complex spatial reasoning and 3D spatial understanding benchmarks. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.15054
PDF
