13 papers
4D Reconstruction with Events & RGB
Dulanga Weerakoon, Darshana Rathnayake, Van Minh Do +7
Reconstructing dynamic 3D scenes over time (4D reconstruction) from a single moving camera is central to robotics and AR/VR applications, yet state-of the-art feed-forward methods…
T-WLA: Bridging Slow Vision and Fast Touch
Kaichen Zhou, Yuzhen Chen, Hannah Yao +14
In contact-rich manipulation, contact conditions can change before a visual policy updates its action plan. Recomputing the plan through the visual policy adds latency, while tacti…
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
Zhiqin Yang, Chenxin Li, Xiaomeng Hu +30
General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To…
AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning
Muyu Xu, Fangneng Zhan, Yu Wei +2
Pose-free feed-forward 3D Gaussian Splatting enables novel view synthesis from uncalibrated multi-view images. Although more views should improve performance, existing methods ofte…
Flow Equivariant World Models: Structured Memory for Dynamic Environments
Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan +2
Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of ex…
GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
Leslie Gu, Junhwa Hur, Charles Herrmann +4
We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and dept…
AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance
Tianling Xu, Shengzhe Gan, Leslie Gu +3
Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes…
Abstract 3D Perception for Spatial Intelligence in Vision-Language Models
Yifan Liu, Fangneng Zhan, Kaichen Zhou +3
Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and e…
RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph
Yifan Liu, Fangneng Zhan, Wanhua Li +3
Estimating robot pose from a monocular RGB image is a challenge in robotics and computer vision. Existing methods typically build networks on top of 2D visual backbones and depend…
3DPR: Single Image 3D Portrait Relight using Generative Priors
Pramod Rao, Abhimitra Meka, Xilong Zhou +11
Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicit…
PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
Kaichen Zhou, Yuhan Wang, Grace Chen +5
Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since the…
Visual Acoustic Fields
Yuelei Li, Hyunjin Kim, Fangneng Zhan +7
Objects produce different sounds when hit, and humans can intuitively infer how an object might sound based on its appearance and material properties. Inspired by this intuition, w…
RAD: A Realistic Multi-View Benchmark for Pose-Agnostic Anomaly Detection
Kaichen Zhou, Xinhai Chang, Taewhan Kim +8
Anomaly detection is essential for robotic perception and industrial inspection, yet most benchmarks are collected under controlled conditions with fixed viewpoints and stable illu…