English
Related papers

Related papers: Foundations of Spatial Perception for Robotics: Hi…

200 papers

We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable and immovable components of the scene. Motivated by the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Prafull Sharma , Ayush Tewari , Yilun Du , Sergey Zakharov , Rares Ambrus , Adrien Gaidon , William T. Freeman , Fredo Durand , Joshua B. Tenenbaum , Vincent Sitzmann

We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to "lift" and integrate 2D visual features over time…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Hsiao-Yu Fish Tung , Ricson Cheng , Katerina Fragkiadaki

Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wenyu Zhang , Wei En Ng , Lixin Ma , Yuwen Wang , Junqi Zhao , Allison Koenecke , Boyang Li , Lu Wang

Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3D-structure-aware representations of scene geometry, these models typically require…

Computer Vision and Pattern Recognition · Computer Science 2020-01-30 Vincent Sitzmann , Michael Zollhöfer , Gordon Wetzstein

Hierarchical structures of motion exist across research fields, including computer vision, graphics, and robotics, where complex dynamics typically arise from coordinated interactions among simpler motion components. Existing methods to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Cheng Zheng , William Koch , Baiang Li , Felix Heide

Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mingfeng Zha , Tianyu Li , Guoqing Wang , Yunqiang Pei , Chaofan Qiao , Jiening Zhang , Yang Yang , Heng Tao Shen

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the underlying structure of the environment is crucial for…

Artificial Intelligence · Computer Science 2023-09-20 Daria de Tinguy , Toon Van de Maele , Tim Verbelen , Bart Dhoedt

Neural reconstruction and rendering strategies have demonstrated state-of-the-art performances due, in part, to their ability to preserve high level shape details. Existing approaches, however, either represent objects as implicit surface…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Angtian Wang , Yuanlu Xu , Nikolaos Sarafianos , Robert Maier , Edmond Boyer , Alan Yuille , Tony Tung

Maps provide robots with crucial environmental knowledge, thereby enabling them to perform interactive tasks effectively. Easily accessing accurate abstract-to-detailed geometric and semantic concepts from maps is crucial for robots to make…

Robotics · Computer Science 2024-03-26 Tianshuai Hu , Jianhao Jiao , Yucheng Xu , Hongji Liu , Sheng Wang , Ming Liu

The deployment of autonomous service robots in human-centric environments is hindered by a critical gap in perception and planning. Traditional navigation systems rely on expensive LiDARs that, while geometrically precise, are semantically…

Robotics · Computer Science 2025-11-11 Praveen Kumar , Tushar Sandhan

Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Xiaolin Hong , Hongwei Yi , Fazhi He , Qiong Cao

3D Scene Graphs (3DSGs) constitute a powerful representation of the physical world, distinguished by their abilities to explicitly model the complex spatial, semantic, and functional relationships between entities, rendering a foundational…

Robotics · Computer Science 2025-12-18 Yunheng Wang , Yixiao Feng , Yuetong Fang , Shuning Zhang , Tan Jing , Jian Li , Xiangrui Jiang , Renjing Xu

Transparent object perception is a rapidly developing research problem in artificial intelligence. The ability to perceive transparent objects enables robots to achieve higher levels of autonomy, unlocking new applications in various…

Robotics · Computer Science 2023-10-18 Jiaqi Jiang , Guanqun Cao , Jiankang Deng , Thanh-Toan Do , Shan Luo

We present a unified and compact scene representation for robotics, where each object in the scene is depicted by a latent code capturing geometry and appearance. This representation can be decoded for various tasks such as novel view…

Recent years have witnessed a rapid growth of applying deep spatiotemporal methods in traffic forecasting. However, the prediction of origin-destination (OD) demands is still a challenging problem since the number of OD pairs is usually…

Machine Learning · Computer Science 2022-05-31 Ruixing Zhang , Liangzhe Han , Boyi Liu , Jiayuan Zeng , Leilei Sun

In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However,…

Robotics · Computer Science 2024-11-22 Junfeng Long , Junli Ren , Moji Shi , Zirui Wang , Tao Huang , Ping Luo , Jiangmiao Pang

Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…

Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly…

Artificial Intelligence · Computer Science 2026-04-14 Shengjie Gong , Wenjie Peng , Hongyuan Chen , Gangyu Zhang , Yunqing Hu , Huiyuan Zhang , Shuangping Huang , Tianshui Chen

Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2D relationships that…

Computer Vision and Pattern Recognition · Computer Science 2017-04-13 Ang Li , Jin Sun , Joe Yue-Hei Ng , Ruichi Yu , Vlad I. Morariu , Larry S. Davis

Comprehensive perception of human beings is the prerequisite to ensure the safety of human-robot interaction. Currently, prevailing visual sensing approach typically involves a single static camera, resulting in a restricted and occluded…

Robotics · Computer Science 2024-03-20 Yuanjiong Ying , Xian Huang , Wei Dong