ICCV 2025 Highlight

[ICCV 2025] Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues

OpenVLA: An open-source vision-language-action model for robotic manipulation.

[NeurIPS 2025] Pixel-Perfect Depth

The official implementation of “Dual Focus-Attention Transformer for Robust Point Cloud Registration”(CVPR2025)

A simple state update rule to enhance length generalization for CUT3R

SLAM-Former: Putting SLAM into One Transformer

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

Kronos: A Foundation Model for the Language of Financial Markets

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Resources for Physics based simulation in Computer Graphics 图形学中物理模拟的资源整理

The official repository of Compact 3D Gaussian Representation for Radiance Field

Continuous Remeshing For Inverse Rendering

Calculate signed distance fields for arbitrary meshes

Source code for "Differentiable Signed Distance Function Rendering" (Siggraph 2022)

RaDe-GS: Rasterizing Depth in Gaussian Splatting

[SIGGRAPH Asia 2022] Differentiable Point-Based Radiance Fields for Efficient View Synthesis

Differentiable Point-based Inverse Rendering [CVPR2024]

This is the project page for 'Resolving Scale Ambiguity in Multi-view 3D Reconstruction using Dual-Pixel Sensors'

A Unified Framework for Surface Reconstruction

Human Performance Modeling and Rendering via Neural Animated Mesh (Published in SIGGRAPH Asia 2022)