8 papers · 1 filter
One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
Xiaohao Xu, Feng Xue, Xiang Li +5
A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth est…
Robust Bayesian Scene Reconstruction with Retrieval-Augmented Priors for Precise Grasping and Planning
Herbert Wright, Weiming Zhi, Martin Matak +2
Constructing 3D representations of object geometry is critical for many robotics tasks, particularly manipulation problems. These representations must be built from potentially noi…
Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
Xiaohao Xu, Feng Xue, Xiang Li +5
Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure. Existing…
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
Xiaohao Xu, Tianyi Zhang, Shibo Zhao +8
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While…
Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
Xiaohao Xu, Ye Li, Tianyi Zhang +3
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of sel…
DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
Tianyi Zhang, Kaining Huang, Weiming Zhi +1
Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this…