The official repository for GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling

Reference PyTorch implementation and models for DINOv3

A differentiable rasterizer used in the project "2D Gaussian Splatting"

🎉 Official code release of "TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors" (ACM MM 2025).

StableDelight: Revealing Hidden Textures by Removing Specular Reflections

[CVPR 2025] IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing

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

[ICLR 2025] Reflective Gaussian Splatting

[CVPR 2025] Ref-GS : Directional Factorization for 2D Gaussian Splatting

Monitor Gaussian Splatting additional real-time viewable and differentiable outputs

Official Code Release for SIGGRAPH Asia 2024 Paper: GS^3: Efficient Relighting with Triple Gaussian Splatting

[ECCV2024] Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing

3D Gaussian Splatting with Deferred Reflection

Code for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

[3DV 2025] Official Implementation of paper "PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization"

A refactored codebase for Gaussian Splatting. Fastest, Better, Modular, Pure Python or CUDA Extension

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

Lightning fast differentiable SSIM.

[ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation

SceneFun3D ToolKit

Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids

[CVPR'24] Group Anything with Radiance Fields

A library for efficient similarity search and clustering of dense vectors.

Official PyTorch Implementation of `Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations`

[ICLR2023] "NeRF-SOS: Any-View Self-supervised Object Segmentation from Complex Real-World Scenes", Zhiwen Fan, Peihao Wang, Xinyu Gong, Yifan Jiang, Dejia Xu, Zhangyang Wang

The implementation of "In-Place Scene Labelling and Understanding with Implicit Scene Representation" [ICCV 2021].

Utilizing segment-anything to help the region selection of 3D point cloud or mesh.