3D 重建

[ECCV 2024] MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

PLVS is a real-time SLAM system with points, lines, volumetric mapping and 3D unsupervised incremental segmentation.

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

Official code of PatchmatchNet (CVPR 2021 Oral)

A lightweight point-based visualization tool used for inspecting Gaussian data, designing camera motion, and exporting setups for external Gaussian renderers.

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (ICCV 2019)

[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

worlds via code, from fable 5.1

End-to-end SFM framework based on GTSAM

This is a 3DGS(3D Gaussian Splatting) viewer built on Three.js, with features for marking, measurements, preset-lod rendering, etc.

INSTA - Instant Volumetric Head Avatars [CVPR2023]

Advanced viewer implementing several rendering methods for 3D gaussians using Vulkan API

Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

🧙🏻‍♂️A list of papers curated for you to dive into the Awesome Radiance Field-based 3D Editing.

📚这个仓库是在arxiv上收集的有关VLN，VLA，World Model，SLAM，Gaussian Splatting,非线性优化等相关论文。每天都会自动更新！issue区域是最新10篇论文

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.

CVPR2023 | MVImgNet: A Large-scale Dataset of Multi-view Images

Official repository of FaceLit: Neural 3D Relightable Faces (CVPR 2023)

LIV-Eye: A Low-Cost LiDAR-Inertial-Visual Fusion 3D Sensor for Robotics and Embodied AI.

A browser-based media editor and agent-friendly foundation for creative tools. AGPL-3.0-only.

SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving

A refactored codebase for Gaussian Splatting. Training 3DGS in 50 seconds!

Pytorch demo code and models for Multi-HMR

End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering

🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

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

[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

Python Wrapper for MeshFix: easily repair holes in surface meshes

Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.

[ICCV2019] Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation.

Code for "Multi-view Reconstruction via SfM-guided Monocular Depth Estimation". CVPR 2025 (Oral Presentation)

"HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting" (NeurIPS 2024)

[ICCV 2023] Official implementation of "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields"

[CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

This repository tracks the latest advancements in 3D Gaussian Splatting from Arxiv, with daily automated updates. Stay up-to-date with cutting-edge research in this exciting field!

[CVPR 2023] vMAP: Vectorised Object Mapping for Neural Field SLAM

Reproducible evaluation of NeRF and 3DGS methods

A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.

[CVPR 2025]MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

[ECCV 2026] Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

[IROS24] Offical Code for "FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework" - Inegrated into Nerfstudio

"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (ECCV 2024)

[ECCV 2026] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

🎞️ [NeurIPS'24] MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views

[ICRA 2024] Chat with NeRF enables users to interact with a NeRF model by typing in natural language.