Cover Image

Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Xiaohao, Xue, Feng, Li, Xiang, Li, Haowei, Yang, Shusheng, Zhang, Tianyi, Johnson-Roberson, Matthew, Huang, Xiaonan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
by: Xu, Xiaohao, et al.
Published: (2024)

From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking
by: Xu, Xiaohao, et al.
Published: (2024)

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
by: Xu, Xiaohao, et al.
Published: (2025)

Customizable Perturbation Synthesis for Robust SLAM Benchmarking
by: Xu, Xiaohao, et al.
Published: (2024)

Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models
by: Zhi, Weiming, et al.
Published: (2024)

Photorealistic Phantom Roads in Real Scenes: Disentangling 3D Hallucinations from Physical Geometry
by: Nguyen, Hoang, et al.
Published: (2025)

DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
by: Zhang, Tianyi, et al.
Published: (2024)

When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
by: Wang, Yunfei, et al.
Published: (2026)

Is Your LiDAR Placement Optimized for 3D Scene Understanding?
by: Li, Ye, et al.
Published: (2024)

Characterizing Lidar Range-Measurement Ambiguity due to Multiple Returns
by: Rife, Jason H., et al.
Published: (2026)

Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration
by: Wang, Jun, et al.
Published: (2026)

Bi-Manual Joint Camera Calibration and Scene Representation
by: Tang, Haozhan, et al.
Published: (2025)

From Single Images to Motion Policies via Video-Generation Environment Representations
by: Zhi, Weiming, et al.
Published: (2025)

Teaching Robots Where To Go And How To Act With Human Sketches via Spatial Diagrammatic Instructions
by: Sun, Qilin, et al.
Published: (2024)

Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation
by: Chu, Wei-Teng, et al.
Published: (2025)

PhotoReg: Photometrically Registering 3D Gaussian Splatting Models
by: Yuan, Ziwen, et al.
Published: (2024)

SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting
by: Liu, Xinyi, et al.
Published: (2024)

Natural Selection via Foundation Models for Soft Robot Evolution
by: Chen, Changhe, et al.
Published: (2025)

Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models
by: Zhang, Tianyi, et al.
Published: (2025)

3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects
by: Zhi, Weiming, et al.
Published: (2024)

Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations
by: Dong, Xiaoxiang, et al.
Published: (2025)

Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
by: Zhi, Weiming, et al.
Published: (2023)

Learning Orbitally Stable Systems for Diagrammatically Teaching
by: Zhi, Weiming, et al.
Published: (2023)

Latent Geometry Beyond Search: Amortizing Planning in World Models
by: Nguyen, Hoang, et al.
Published: (2026)

GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction
by: Tang, Haozhan, et al.
Published: (2025)

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity
by: Yin, Guang, et al.
Published: (2025)

Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
by: Lin, Xingyao, et al.
Published: (2025)

Masked Depth Modeling for Spatial Perception
by: Tan, Bin, et al.
Published: (2026)

Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning
by: Zheng, Gehan, et al.
Published: (2026)

Robust Bayesian Scene Reconstruction with Retrieval-Augmented Priors for Precise Grasping and Planning
by: Wright, Herbert, et al.
Published: (2024)

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
by: Bian, Siyuan, et al.
Published: (2026)

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
by: Kong, Lingdong, et al.
Published: (2023)

Reasoning about the Unseen for Efficient Outdoor Object Navigation
by: Xie, Quanting, et al.
Published: (2023)

Cross-Modal Instructions for Robot Motion Generation
by: Barron, William, et al.
Published: (2025)

Influence of Camera-LiDAR Configuration on 3D Object Detection for Autonomous Driving
by: Li, Ye, et al.
Published: (2023)

JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
by: Zeng, Shuang, et al.
Published: (2025)

Resolving Positional Ambiguity in Dialogues by Vision-Language Models for Robot Navigation
by: Chen, Kuan-Lin, et al.
Published: (2024)

Feeling Optimistic? Ambiguity Attitudes for Online Decision Making
by: Beard, Jared J., et al.
Published: (2023)

FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation
by: Li, Yishu, et al.
Published: (2024)

DeFM: Learning Foundation Representations from Depth for Robotics
by: Patel, Manthan, et al.
Published: (2026)