Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Segment Any 4D Gaussians

3D Gaussian Splatting adapted version of OmniSeg3D (CVPR2024)

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

The official implementation of SAGA (Segment Any 3D GAussians)

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

LaTeX template for dissertations in Peking University

[CVPR 2024] DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

A unified framework for 3D content generation.

[ICCV 2023] Official code for NeuS2

Code release for NeuS

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Implement custom operators in PyTorch with cuda/c++

C++ extensions in PyTorch

Convolutional Neural Network with CUDA (MNIST 99.23%)

RaDe-GS: Rasterizing Depth in Gaussian Splatting

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Let us control diffusion models!

[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

SAM with text prompt

YOLOv10: Real-Time End-to-End Object Detection

Official repository of HUGS: Human Gaussian Splats (CVPR 2024)