This repository provides a reproducible pipeline to compute the Video Fidelity Score (VFS) for a single real and a single fake video.

[CVPR'25] How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions

A programming framework for agentic AI

NGINX-based Media Streaming Server

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

This repository is for active development of the Azure SDK for Python. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/python/azure/ or our v…

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

[NeurIPS 2024] OnlineTAS: An Online Baseline for Temporal Action Segmentation

Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation

PyTorch code and models for VJEPA2 self-supervised learning from video.

My own 3D game engine

A reimplementation of Stable Diffusion 3.5 in pure PyTorch

SoTA open-source TTS

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] Code for Segment Any Motion in Videos

Testplan, a multi-testing framework, because unit tests can only go so far..

Open-source unified multimodal model

Extract the main content from web pages.

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality…

GDPR, WCAG 2.2 AA, and EAA compliant, self-hosted CAPTCHA alternative with PoW mechanism.

Run Segment Anything Model 2 on a live video stream

An extremely fast Python type checker and language server, written in Rust.

[WACV 2023] Interacting Hand-Object Pose Estimation via Dense Mutual Attention

Awesome work on hand pose estimation/tracking

Blender add-on for editing scenes reconstructed with SuGaR or Gaussian Frosting.