Point_Cloud
-
Towards Zero-shot 3D Anomaly Localization
2024-12-05 16:25:27Yizhou Wang, Kuan-Chuan Peng, Yun FuAbstract
3D anomaly detection and localization is of great significance for industrial inspection. Prior 3D anomaly detection and localization methods focus on the setting that the testing data share the same category as the training data which is normal. However, in real-world applications, the normal training data for the target 3D objects can be unavailable due to issues like data privacy or export control regulation. To tackle these challenges, we identify a new task -- zero-shot 3D anomaly detection and localization, where the training and testing classes do not overlap. To this end, we design 3DzAL, a novel patch-level contrastive learning framework based on pseudo anomalies generated using the inductive bias from task-irrelevant 3D xyz data to learn more representative feature representations. Furthermore, we train a normalcy classifier network to classify the normal patches and pseudo anomalies and utilize the classification result jointly with feature distance to design anomaly scores. Instead of directly using the patch point clouds, we introduce adversarial perturbations to the input patch xyz data before feeding into the 3D normalcy classifier for the classification-based anomaly score. We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.
Abstract (translated)
URL
https://arxiv.org/abs/2412.04304
PDF
-
3D Part Segmentation via Geometric Aggregation of 2D Visual Features
2024-12-05 15:27:58Marco Garosi, Riccardo Tedoldi, Davide Boscaini, Massimiliano Mancini, Nicu Sebe, Fabio PoiesiAbstract
Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios. Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts. However, naively applying VLMs in this context introduces several drawbacks, such as the need for meticulous prompt engineering, and fails to leverage the 3D geometric structure of objects. To address these limitations, we propose COPS, a COmprehensive model for Parts Segmentation that blends the semantics extracted from visual concepts and 3D geometry to effectively identify object parts. COPS renders a point cloud from multiple viewpoints, extracts 2D features, projects them back to 3D, and uses a novel geometric-aware feature aggregation procedure to ensure spatial and semantic consistency. Finally, it clusters points into parts and labels them. We demonstrate that COPS is efficient, scalable, and achieves zero-shot state-of-the-art performance across five datasets, covering synthetic and real-world data, texture-less and coloured objects, as well as rigid and non-rigid shapes. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.04247
PDF
-
CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
2024-12-05 12:38:18Thomas Walker, Salvatore Esposito, Daniel Rebain, Amir Vaxman, Arno Onken, Changjian Li, Oisin Mac AodhaAbstract
Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the-box point cloud reconstruction methods can often fail due to the data sparsity between slicing planes, while current bespoke methods struggle to reconstruct thin geometric structures and preserve topological continuity. This is important for medical applications where thin vessel structures are present in CT and MRI scans. This paper introduces \method, a novel approach for extracting a 3D signed distance field from 2D signed distances generated from planar contours. Our approach makes the training of neural SDFs contour-aware by using losses designed for the case where geometry is known within 2D slices. Our results demonstrate a significant improvement over existing methods, effectively reconstructing thin structures and producing accurate 3D models without the interpolation artifacts or over-smoothing of prior approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2412.04120
PDF
-
4D SlingBAG: spatial-temporal coupled Gaussian ball for large-scale dynamic 3D photoacoustic iterative reconstruction
2024-12-05 06:15:26Shuang Li, Yibing Wang, Jian Gao, Chulhong Kim, Seongwook Choi, Yu Zhang, Qian Chen, Yao Yao, Changhui LiAbstract
Large-scale dynamic three-dimensional (3D) photoacoustic imaging (PAI) is significantly important in clinical applications. In practical implementations, large-scale 3D real-time PAI systems typically utilize sparse two-dimensional (2D) sensor arrays with certain angular deficiencies, necessitating advanced iterative reconstruction (IR) algorithms to achieve quantitative PAI and reduce reconstruction artifacts. However, for existing IR algorithms, multi-frame 3D reconstruction leads to extremely high memory consumption and prolonged computation time, with limited consideration of the spatial-temporal continuity between data frames. Here, we propose a novel method, named the 4D sliding Gaussian ball adaptive growth (4D SlingBAG) algorithm, based on the current point cloud-based IR algorithm sliding Gaussian ball adaptive growth (SlingBAG), which has minimal memory consumption among IR methods. Our 4D SlingBAG method applies spatial-temporal coupled deformation functions to each Gaussian sphere in point cloud, thus explicitly learning the deformations features of the dynamic 3D PA scene. This allows for the efficient representation of various physiological processes (such as pulsation) or external pressures (e.g., blood perfusion experiments) contributing to changes in vessel morphology and blood flow during dynamic 3D PAI, enabling highly efficient IR for dynamic 3D PAI. Simulation experiments demonstrate that 4D SlingBAG achieves high-quality dynamic 3D PA reconstruction. Compared to performing reconstructions by using SlingBAG algorithm individually for each frame, our method significantly reduces computational time and keeps a extremely low memory consumption. The project for 4D SlingBAG can be found in the following GitHub repository: \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03898
PDF
-
Coordinate In and Value Out: Training Flow Transformers in Ambient Space
2024-12-05 01:00:07Yuyang Wang, Anurag Ranjan, Josh Susskind, Miguel Angel BautistaAbstract
Flow matching models have emerged as a powerful method for generative modeling on domains like images or videos, and even on unstructured data like 3D point clouds. These models are commonly trained in two stages: first, a data compressor (i.e., a variational auto-encoder) is trained, and in a subsequent training stage a flow matching generative model is trained in the low-dimensional latent space of the data compressor. This two stage paradigm adds complexity to the overall training recipe and sets obstacles for unifying models across data domains, as specific data compressors are used for different data modalities. To this end, we introduce Ambient Space Flow Transformers (ASFT), a domain-agnostic approach to learn flow matching transformers in ambient space, sidestepping the requirement of training compressors and simplifying the training process. We introduce a conditionally independent point-wise training objective that enables ASFT to make predictions continuously in coordinate space. Our empirical results demonstrate that using general purpose transformer blocks, ASFT effectively handles different data modalities such as images and 3D point clouds, achieving strong performance in both domains and outperforming comparable approaches. ASFT is a promising step towards domain-agnostic flow matching generative models that can be trivially adopted in different data domains.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03791
PDF
-
Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter
2024-12-04 17:59:04Hermes McGriff, Renato Martins, Nicolas Andreff, Cedric DemonceauxAbstract
This paper presents a dense depth estimation approach from light-field (LF) images that is able to compensate for strong rolling shutter (RS) effects. Our method estimates RS compensated views and dense RS compensated disparity maps. We present a two-stage method based on a 2D Gaussians Splatting that allows for a ``render and compare" strategy with a point cloud formulation. In the first stage, a subset of sub-aperture images is used to estimate an RS agnostic 3D shape that is related to the scene target shape ``up to a motion". In the second stage, the deformation of the 3D shape is computed by estimating an admissible camera motion. We demonstrate the effectiveness and advantages of this approach through several experiments conducted for different scenes and types of motions. Due to lack of suitable datasets for evaluation, we also present a new carefully designed synthetic dataset of RS LF images. The source code, trained models and dataset will be made publicly available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2412.03518
PDF
-
AffordDP: Generalizable Diffusion Policy with Transferable Affordance
2024-12-04 09:08:07Shijie Wu, Yihang Zhu, Yunao Huang, Kaizhen Zhu, Jiayuan Gu, Jingyi Yu, Ye Shi, Jingya WangAbstract
Diffusion-based policies have shown impressive performance in robotic manipulation tasks while struggling with out-of-domain distributions. Recent efforts attempted to enhance generalization by improving the visual feature encoding for diffusion policy. However, their generalization is typically limited to the same category with similar appearances. Our key insight is that leveraging affordances--manipulation priors that define "where" and "how" an agent interacts with an object--can substantially enhance generalization to entirely unseen object instances and categories. We introduce the Diffusion Policy with transferable Affordance (AffordDP), designed for generalizable manipulation across novel categories. AffordDP models affordances through 3D contact points and post-contact trajectories, capturing the essential static and dynamic information for complex tasks. The transferable affordance from in-domain data to unseen objects is achieved by estimating a 6D transformation matrix using foundational vision models and point cloud registration techniques. More importantly, we incorporate affordance guidance during diffusion sampling that can refine action sequence generation. This guidance directs the generated action to gradually move towards the desired manipulation for unseen objects while keeping the generated action within the manifold of action space. Experimental results from both simulated and real-world environments demonstrate that AffordDP consistently outperforms previous diffusion-based methods, successfully generalizing to unseen instances and categories where others fail.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03142
PDF
-
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
2024-12-04 06:26:12Runjian Chen, Hang Zhang, Avinash Ravichandran, Wenqi Shao, Alex Wong, Ping LuoAbstract
Unsupervised 3D representation learning via masked-and-reconstruction with differentiable rendering is promising to reduce the labeling burden for fusion 3D perception. However, previous literature conduct pre-training for different modalities separately because of the hight GPU memory consumption. Consequently, the interaction between the two modalities (images and point clouds) is neglected during pre-training. In this paper, we explore joint unsupervised pre-training for fusion 3D perception via differentiable rendering and propose CLAP, short for Curvature sampLing and swApping Prototype assignment prediction. The contributions are three-fold. 1) To overcome the GPU memory consumption problem, we propose Curvature Sampling to sample the more informative points/pixels for pre-training. 2) We propose to use learnable prototypes to represent parts of the scenes in a common feature space and bring the idea of swapping prototype assignment prediction to learn the interaction between the two modalities. 3) To further optimize learnable prototypes, we propose an Expectation-Maximization training scheme to maximize the similarity between embeddings and prototypes, followed by a Gram Matrix Regularization Loss to avoid collapse. Experiment results on NuScenes show that CLAP achieves 300% more performance gain as compared to previous SOTA 3D pre-training method via differentiable rendering. Codes and models will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03059
PDF
-
Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
2024-12-04 06:20:51Marzieh Mohammadi, Amir SalarpourAbstract
This paper introduces Point-GN, a novel non-parametric network for efficient and accurate 3D point cloud classification. Unlike conventional deep learning models that rely on a large number of trainable parameters, Point-GN leverages non-learnable components-specifically, Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and Gaussian Positional Encoding (GPE)-to extract both local and global geometric features. This design eliminates the need for additional training while maintaining high performance, making Point-GN particularly suited for real-time, resource-constrained applications. We evaluate Point-GN on two benchmark datasets, ModelNet40 and ScanObjectNN, achieving classification accuracies of 85.29% and 85.89%, respectively, while significantly reducing computational complexity. Point-GN outperforms existing non-parametric methods and matches the performance of fully trained models, all with zero learnable parameters. Our results demonstrate that Point-GN is a promising solution for 3D point cloud classification in practical, real-time environments.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03056
PDF
-
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
2024-12-04 06:17:24Runjian Chen, Hyoungseob Park, Bo Zhang, Wenqi Shao, Ping Luo, Alex WongAbstract
Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR perception via pretrained weights. Almost all existing work focus on a single frame of LiDAR point cloud and neglect the temporal LiDAR sequence, which naturally accounts for object motion (and their semantics). Instead, we propose TREND, namely Temporal REndering with Neural fielD, to learn 3D representation via forecasting the future observation in an unsupervised manner. Unlike existing work that follows conventional contrastive learning or masked auto encoding paradigms, TREND integrates forecasting for 3D pre-training through a Recurrent Embedding scheme to generate 3D embedding across time and a Temporal Neural Field to represent the 3D scene, through which we compute the loss using differentiable rendering. To our best knowledge, TREND is the first work on temporal forecasting for unsupervised 3D representation learning. We evaluate TREND on downstream 3D object detection tasks on popular datasets, including NuScenes, Once and Waymo. Experiment results show that TREND brings up to 90% more improvement as compared to previous SOTA unsupervised 3D pre-training methods and generally improve different downstream models across datasets, demonstrating that indeed temporal forecasting brings improvement for LiDAR perception. Codes and models will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03054
PDF
-
Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation
2024-12-04 06:12:19Md Meraz, Md Afzal Ansari, Mohammed Javed, Pavan ChakrabortyAbstract
In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for classification tasks remains crucial. This paper presents Point-GR, a novel deep learning architecture designed explicitly to transform unordered raw point clouds into higher dimensions while preserving local geometric features. It introduces residual-based learning within the network to mitigate the point permutation issues in point cloud data. The proposed Point-GR network significantly reduced the number of network parameters in Classification and Part-Segmentation compared to baseline graph-based networks. Notably, the Point-GR model achieves a state-of-the-art scene segmentation mean IoU of 73.47% on the S3DIS benchmark dataset, showcasing its effectiveness. Furthermore, the model shows competitive results in Classification and Part-Segmentation tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03052
PDF
-
QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives
2024-12-04 03:35:08Ji Wu, Huai Yu, Shu Han, Xi-Meng Cai, Ming-Feng Wang, Wen Yang, Gui-Song XiaAbstract
In the realm of large-scale point cloud registration, designing a compact symbolic representation is crucial for efficiently processing vast amounts of data, ensuring registration robustness against significant viewpoint variations and occlusions. This paper introduces a novel point cloud registration method, i.e., QuadricsReg, which leverages concise quadrics primitives to represent scenes and utilizes their geometric characteristics to establish correspondences for 6-DoF transformation estimation. As a symbolic feature, the quadric representation fully captures the primary geometric characteristics of scenes, which can efficiently handle the complexity of large-scale point clouds. The intrinsic characteristics of quadrics, such as types and scales, are employed to initialize correspondences. Then we build a multi-level compatibility graph set to find the correspondences using the maximum clique on the geometric consistency between quadrics. Finally, we estimate the 6-DoF transformation using the quadric correspondences, which is further optimized based on the quadric degeneracy-aware distance in a factor graph, ensuring high registration accuracy and robustness against degenerate structures. We test on 5 public datasets and the self-collected heterogeneous dataset across different LiDAR sensors and robot platforms. The exceptional registration success rates and minimal registration errors demonstrate the effectiveness of QuadricsReg in large-scale point cloud registration scenarios. Furthermore, the real-world registration testing on our self-collected heterogeneous dataset shows the robustness and generalization ability of QuadricsReg on different LiDAR sensors and robot platforms. The codes and demos will be released at \url{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02998
PDF
-
Adaptive LiDAR Odometry and Mapping for Autonomous Agricultural Mobile Robots in Unmanned Farms
2024-12-03 23:04:49Hanzhe Teng, Yipeng Wang, Dimitrios Chatziparaschis, Konstantinos KarydisAbstract
Unmanned and intelligent agricultural systems are crucial for enhancing agricultural efficiency and for helping mitigate the effect of labor shortage. However, unlike urban environments, agricultural fields impose distinct and unique challenges on autonomous robotic systems, such as the unstructured and dynamic nature of the environment, the rough and uneven terrain, and the resulting non-smooth robot motion. To address these challenges, this work introduces an adaptive LiDAR odometry and mapping framework tailored for autonomous agricultural mobile robots operating in complex agricultural environments. The proposed framework consists of a robust LiDAR odometry algorithm based on dense Generalized-ICP scan matching, and an adaptive mapping module that considers motion stability and point cloud consistency for selective map updates. The key design principle of this framework is to prioritize the incremental consistency of the map by rejecting motion-distorted points and sparse dynamic objects, which in turn leads to high accuracy in odometry estimated from scan matching against the map. The effectiveness of the proposed method is validated via extensive evaluation against state-of-the-art methods on field datasets collected in real-world agricultural environments featuring various planting types, terrain types, and robot motion profiles. Results demonstrate that our method can achieve accurate odometry estimation and mapping results consistently and robustly across diverse agricultural settings, whereas other methods are sensitive to abrupt robot motion and accumulated drift in unstructured environments. Further, the computational efficiency of our method is competitive compared with other methods. The source code of the developed method and the associated field dataset are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02899
PDF
-
Optimized CNNs for Rapid 3D Point Cloud Object Recognition
2024-12-03 21:42:30Tianyi Lyu, Dian Gu, Peiyuan Chen, Yaoting Jiang, Zhenhong Zhang, Huadong Pang, Li Zhou, Yiping DongAbstract
This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that capitalize on the typical sparsity observed in input data. We explore the trade-off between accuracy and speed across diverse network architectures and advocate for integrating an $\mathcal{L}_1$ penalty on filter activations to augment sparsity within intermediate layers. This research pioneers the proposal of sparse convolutional layers combined with $\mathcal{L}_1$ regularization to effectively handle large-scale 3D data processing. Our method's efficacy is demonstrated on the MVTec 3D-AD object detection benchmark. The Vote3Deep models, with just three layers, outperform the previous state-of-the-art in both laser-only approaches and combined laser-vision methods. Additionally, they maintain competitive processing speeds. This underscores our approach's capability to substantially enhance detection performance while ensuring computational efficiency suitable for real-time applications.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02855
PDF
-
MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
2024-12-03 18:18:33Zhaofeng Hu, Sifan Zhou, Shibo Zhao, Zhihang YuanAbstract
3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02734
PDF
-
BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding
2024-12-03 13:34:42Chenguang Huang, Shengchao Yan, Wolfram BurgardAbstract
Dynamic scene understanding remains a persistent challenge in robotic applications. Early dynamic mapping methods focused on mitigating the negative influence of short-term dynamic objects on camera motion estimation by masking or tracking specific categories, which often fall short in adapting to long-term scene changes. Recent efforts address object association in long-term dynamic environments using neural networks trained on synthetic datasets, but they still rely on predefined object shapes and categories. Other methods incorporate visual, geometric, or semantic heuristics for the association but often lack robustness. In this work, we introduce BYE, a class-agnostic, per-scene point cloud encoder that removes the need for predefined categories, shape priors, or extensive association datasets. Trained on only a single sequence of exploration data, BYE can efficiently perform object association in dynamically changing scenes. We further propose an ensembling scheme combining the semantic strengths of Vision Language Models (VLMs) with the scene-specific expertise of BYE, achieving a 7% improvement and a 95% success rate in object association tasks. Code and dataset are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02449
PDF
-
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
2024-12-03 11:50:16Changli Wu, Qi Chen, Jiayi Ji, Haowei Wang, Yiwei Ma, You Huang, Gen Luo, Hao Fei, Xiaoshuai Sun, Rongrong JiAbstract
3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounter issues like over-segmentation or mis-segmentation, due to insufficient emphasis on spatial information of instances. In this paper, we introduce a Rule-Guided Spatial Awareness Network (RG-SAN) by utilizing solely the spatial information of the target instance for supervision. This approach enables the network to accurately depict the spatial relationships among all entities described in the text, thus enhancing the reasoning capabilities. The RG-SAN consists of the Text-driven Localization Module (TLM) and the Rule-guided Weak Supervision (RWS) strategy. The TLM initially locates all mentioned instances and iteratively refines their positional information. The RWS strategy, acknowledging that only target objects have supervised positional information, employs dependency tree rules to precisely guide the core instance's positioning. Extensive testing on the ScanRefer benchmark has shown that RG-SAN not only establishes new performance benchmarks, with an mIoU increase of 5.1 points, but also exhibits significant improvements in robustness when processing descriptions with spatial ambiguity. All codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02402
PDF
-
Single-Shot Metric Depth from Focused Plenoptic Cameras
2024-12-03 11:21:17Blanca Lasheras-Hernandez, Klaus H. Strobl, Sergio Izquierdo, Tim Bodenm\"uller, Rudolph Triebel, Javier CiveraAbstract
Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment. Traditional range imaging setups, such as stereo or structured light cameras, face hassles including calibration, occlusions, and hardware demands, with accuracy limited by the baseline between cameras. Single- and multi-view monocular depth offers a more compact alternative, but is constrained by the unobservability of the metric scale. Light field imaging provides a promising solution for estimating metric depth by using a unique lens configuration through a single device. However, its application to single-view dense metric depth is under-addressed mainly due to the technology's high cost, the lack of public benchmarks, and proprietary geometrical models and software. Our work explores the potential of focused plenoptic cameras for dense metric depth. We propose a novel pipeline that predicts metric depth from a single plenoptic camera shot by first generating a sparse metric point cloud using machine learning, which is then used to scale and align a dense relative depth map regressed by a foundation depth model, resulting in dense metric depth. To validate it, we curated the Light Field & Stereo Image Dataset (LFS) of real-world light field images with stereo depth labels, filling a current gap in existing resources. Experimental results show that our pipeline produces accurate metric depth predictions, laying a solid groundwork for future research in this field.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02386
PDF
-
SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images
2024-12-03 03:56:01Junqiu Yu, Xinlin Ren, Yongchong Gu, Haitao Lin, Tianyu Wang, Yi Zhu, Hang Xu, Yu-Gang Jiang, Xiangyang Xue, Yanwei FuAbstract
Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes, limiting their effectiveness in changeable environments. In contrast, we propose SparseGrasp, a novel open-vocabulary robotic grasping system that operates efficiently with sparse-view RGB images and handles scene updates fastly. Our system builds upon and significantly enhances existing computer vision modules in robotic learning. Specifically, SparseGrasp utilizes DUSt3R to generate a dense point cloud as the initialization for 3D Gaussian Splatting (3DGS), maintaining high fidelity even under sparse supervision. Importantly, SparseGrasp incorporates semantic awareness from recent vision foundation models. To further improve processing efficiency, we repurpose Principal Component Analysis (PCA) to compress features from 2D models. Additionally, we introduce a novel render-and-compare strategy that ensures rapid scene updates, enabling multi-turn grasping in changeable environments. Experimental results show that SparseGrasp significantly outperforms state-of-the-art methods in terms of both speed and adaptability, providing a robust solution for multi-turn grasping in changeable environment.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02140
PDF
-
GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
2024-12-03 03:34:18Yifan Jiao, Yunhao Li, Junhua Ding, Qing Yang, Song Fu, Heng Fan, Libo ZhangAbstract
In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB image, and depth. This allows GSOT3D to support various 3D tracking tasks, such as single-modal 3D SOT on PC and multi-modal 3D SOT on RGB-PC or RGB-D, and thus greatly broadens research directions for 3D object tracking. To provide highquality per-frame 3D annotations, all sequences are labeled manually with multiple rounds of meticulous inspection and refinement. To our best knowledge, GSOT3D is the largest benchmark dedicated to various generic 3D object tracking tasks. To understand how existing 3D trackers perform and to provide comparisons for future research on GSOT3D, we assess eight representative point cloud-based tracking models. Our evaluation results exhibit that these models heavily degrade on GSOT3D, and more efforts are required for robust and generic 3D object tracking. Besides, to encourage future research, we present a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin. By releasing GSOT3D, we expect to advance further 3D tracking in future research and applications. Our benchmark and model as well as the evaluation results will be publicly released at our webpage this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02129
PDF
