ScanNet alternatives for AI agents.

Bundler Structure from Motion Toolkit

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

📚 Jupyter notebook tutorials for OpenVINO™

Ray tracing and hybrid rasterization of Gaussian particles

记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

Tracking Any Point (TAP)

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Training library for local feature detection and matching

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

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

OpenMMLab Foundational Library for Training Deep Learning Models

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]