Stars
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
Fine-Grained Open Domain Image Animation with Motion Guidance
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds
[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"
Blender Python scripts for rendering images directly from command-line interface
3DGS Render by KIRI Engine
Some simple Blender scripts for rendering paper figures
[NeurIPS'23] Emergent Correspondence from Image Diffusion
[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Stable Video Diffusion Training Code and Extensions.
DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting
[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
A set of tools to visualize and interact with sequences of 3D data.
[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.
MANO layer for PyTorch, generating hand meshes as a differentiable layer
Project for paper "Learning 3D Human Dynamics from Video"
Official implementation of SEED-LLaMA (ICLR 2024).
Pippo: High-Resolution Multi-View Humans from a Single Image
Estimate absolute 3D human poses from RGB images.