Anpei Chen

R3. Official implementation of R^3: 3D Reconstruction via Relative Regression.

awesome-Feedforward-3D-and-NVS. [CGF] A curated list of papers on feed-forward 3D reconstruction and novel view synthesis.

Motion324. [CVPR 2026] 3D Motion Reconstruction for 4D Synthesis

infinigen. Infinite Photorealistic Worlds using Procedural Generation

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

Cupid. [CVPR'26 Highlight] Cupid: A 3D generator that links 2D image with camera

Human3R. [ICLR 2026] An unified model for 4D human-scene reconstruction

TTT3R. [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

GaVS. [SIGGRAPH 2025] Official Repo for Paper - GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

unified_video_action. Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

attention-gym. Helpful tools and examples for working with flex-attention

loftup. [ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"

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

ReCamMaster. [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

LVSM. [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

See3D. [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Easi3R. [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.

GenFusion. [CVPR 2025] GenFusion: Closing the Loop between Reconstruction and Generation via Videos

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Feat2GS. [CVPR2025] Feat2GS: Probing Visual Foundation Models with Gaussian Splatting

vk_gltf_renderer. Vulkan ray tracing glTF 2.0 renderer — RTX path tracer with PBR materials, AI denoising (DLSS, OptiX), and scene editing. NVIDIA open-source sample.

diso. Differentiable Iso-Surface Extraction Package (DISO)

LaRa. [ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model

Omost. Your image is almost there!

diff-surfel-rasterization. A differentiable rasterizer used in the project "2D Gaussian Splatting"

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

SpacetimeGaussians. [CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

OpenLRM. An open-source impl. of Large Reconstruction Models

nelf-pro. [CVPR 2024] Official repo for paper NeLF-Pro: Neural Light Field Probes

Marigold. [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

murf. [CVPR'24] MuRF: Multi-Baseline Radiance Fields

GraphDreamer. [CVPR'24] GraphDreamer: a novel framework of generating compositional 3D scenes from scene graphs.

mip-splatting. [CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

NeuRBF. Python

factor-fields. [SIGGRAPH 2023] We provide a unified formula for neural fields (Factor Fields) and a novel dictionary factorization (Dictionary Fields)

nerfacc. A General NeRF Acceleration Toolbox in PyTorch.

threestudio. A unified framework for 3D content generation.

SSDNeRF. [ICCV 2023] Single-Stage Diffusion NeRF

tyro. CLI interfaces & config objects, from types

tensorf-jax. Unofficial implementation of Tensorial Radiance Fields (Chen & Xu ‘22)

sdfstudio. A Unified Framework for Surface Reconstruction

nerfstudio. A collaboration friendly studio for NeRFs

cv-arxiv-daily. 🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

differentiable-sdf-rendering. Source code for "Differentiable Signed Distance Function Rendering" (Siggraph 2022)

unimatch. [TPAMI'23] Unifying Flow, Stereo and Depth Estimation

nerf. Code release for NeRF (Neural Radiance Fields)

PREF. PREF: Phasorial Embedding Fields for Compact Neural Representations

monosdf. [NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

TensoRF. [ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

awesome-3D-generation. A curated list of awesome 3d generation papers

DirectVoxGO. Direct voxel grid optimization for fast radiance field reconstruction.

svox2. Plenoxels: Radiance Fields without Neural Networks

sof. Training and testing scripts for Semantic Occupancy Field.

ManiSkill-Legacy. SAPIEN Manipulation Skill Benchmark (NeurIPS 2021 Track on Datasets and Benchmarks)

gnerf. [ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )

awesome-NeRF. A curated list of awesome neural radiance fields papers

mvsnerf. [ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

SphericalHarmonics. Spherical harmonics for radiance maps in python (numpy)

PlenOctrees_NeRF-SH. PlenOctree Extraction algorithm

IBRNet. Python

a-toy-fluid-engine. try to reimplement Euler based fluid

3D-Face. A simple python script for parametric face model estimation from single or multiple images

CVPR2024-Paper-Code-Interpretation. cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

sofgan. [TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling

relightable-nr. A Neural Rendering Framework for Free-Viewpoint Relighting (CVPR 2020)

NOPC. Pytorch implementation of Neural Opacity Point Cloud.

PCPR. Differentiable point cloud projection and render

stylegan2-pytorch. Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

eos. A lightweight 3D Morphable Face Model library in modern C++

face-datasets.

tungsten. High performance physically based renderer in C++11

trimesh. Python library for loading and using triangular meshes.

Facial_Details_Synthesis. [ICCV2019 Oral] Photo-Realistic Facial Details Synthesis from Single Image

eos-expression-aware-proxy. Expression-Aware Proxy Generation part of the paper Photo-Realistic Facial Details Synthesis From Single Image

SLN-Amodal. [ACM MM2019] Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

face_rendering. face rendering

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration