3d-reconstruction

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Official implement of VGGT-Long

A toolbox for 3D visual mapping, localization, and SfM with structured geometric features (points, lines, planes, vanishing points, wireframes, etc.).

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

Demonstration of different algorithms and operations on faces. Star the repo⭐

Implementations of NeRF variants based on Taichi + PyTorch

3D geometry processing SDK: fast mesh boolean, mesh repair, decimation, remeshing, offset, point cloud triangulation and ICP registration. C++ with Python, C#, C and JavaScript bindings.

[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

Level of Gaussians

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.

ImMesh: An Immediate LiDAR Localization and Meshing Framework

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

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

Collecting papers about new view synthesis

[TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

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

[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

News: the 10k dataset is ready for download.

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)

Python library for fitting 3D primitive shapes to point clouds with RANSAC. Detect planes, spheres, cylinders, cuboids, circles, and lines.

(ICLR2026) ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation

Streaming 3D reconstruction from only video input: Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

[SIGGRAPH2023] NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images