3d Depth Estimation


3D depth estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images.

Struct2D: A Perception-Guided Framework for Spatial Reasoning in Large Multimodal Models

Add code
Jun 04, 2025
Viaarxiv icon

Object Concepts Emerge from Motion

Add code
May 27, 2025
Viaarxiv icon

GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion

Add code
May 29, 2025
Viaarxiv icon

Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning

Add code
May 27, 2025
Viaarxiv icon

From Single Images to Motion Policies via Video-Generation Environment Representations

Add code
May 25, 2025
Viaarxiv icon

Spatial RoboGrasp: Generalized Robotic Grasping Control Policy

Add code
May 27, 2025
Viaarxiv icon

4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians

Add code
May 28, 2025
Viaarxiv icon

Joint Depth and Reflectivity Estimation using Single-Photon LiDAR

Add code
May 19, 2025
Viaarxiv icon

Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss

Add code
May 28, 2025
Viaarxiv icon

A Shape-Aware Total Body Photography System for In-focus Surface Coverage Optimization

Add code
May 22, 2025
Viaarxiv icon