9 papers
PhysReal: Learning Real-World Deformable Object Physics via Hybrid Constitutive Modeling
Yinan Deng, Jianqiao Song, Yisi Zhang +3
Learning physically plausible dynamics from visual observations is essential for interactive world models and embodied agents. However, modeling real-world deformable objects remai…
PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
Yinan Deng, Jianyu Dou, Jiahui Wang +3
Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scen…
DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
Jiahui Wang, Changhao Chen
Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overh…
OmniMap: A General Mapping Framework Integrating Optics, Geometry, and Semantics
Yinan Deng, Yufeng Yue, Jianyu Dou +5
Robotic systems demand accurate and comprehensive 3D environment perception, requiring simultaneous capture of photo-realistic appearance (optical), precise layout shape (geometric…
OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
Jianyu Dou, Yinan Deng, Jiahui Wang +3
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semant…
LCP-Fusion: A Neural Implicit SLAM with Enhanced Local Constraints and Computable Prior
Jiahui Wang, Yinan Deng, Yi Yang +1
Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nev…
OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
Yinan Deng, Jiahui Wang, Jingyu Zhao +3
In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities…
LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating
Yufeng Yue, Yinan Deng, Jiahui Wang +1
Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which ha…
OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
Yinan Deng, Jiahui Wang, Jingyu Zhao +4
Environment representations endowed with sophisticated semantics are pivotal for facilitating seamless interaction between robots and humans, enabling them to effectively carry out…