Habitat Lab alternatives for AI agents.

Vision-and-Language Navigation in Continuous Environments using Habitat

Scenic: A Jax Library for Computer Vision Research and Beyond

OpenMMLab Foundational Library for Training Deep Learning Models

Gibson Environments: Real-World Perception for Embodied Agents

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

Superfast AI decision making and intelligent processing of multi-modal data.

Demo for the "Talking Head Anime from a Single Image."

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/

Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

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

Training library for local feature detection and matching

[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.

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

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

[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.