Stars
Synthetic Faces High Quality (SFHQ) Dataset. 425,000 curated 1024x1024 synthetic face images
open Multi-View Stereo reconstruction library
CoTracker is a model for tracking any point (pixel) on a video.
Source code for Fathony, Sahu, Willmott, & Kolter, "Multiplicative Filter Networks", ICLR 2021.
[NeurIPS 2024]GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
[3DV'25] 3D Reconstruction with Spatial Memory
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Source code for "Interactive All-Hex Meshing via Cuboid Decomposition" [SIGGRAPH Asia 2021].
[ICCV2023] GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering
Some simple Blender scripts for rendering paper figures
Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!
A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]
ingra14m / depth-diff-gaussian-rasterization
Forked from graphdeco-inria/diff-gaussian-rasterizationAn extension to official diff-gaussian-rasterization with forward and backward depth pass
A list of awesome traditional (core) OS paper before the LLM era
🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
[SIGGRAPH Asia 2023] Code for our paper "RT-Octree: Accelerate PlenOctree Rendering with Batched Regular Tracking and Neural Denoising for Real-time Neural Radiance Fields"