Lists (1)
Stars
Code of paper "A Doubly Decoupled Network for Edge Detection"
Halpe: full body human pose estimation and human-object interaction detection dataset
Template matching for rotation using Radon transforms.
🔥 [ICCV 2025 Highlight] Official open-source repo for LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition
[ICCV 2023] TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"
CGo なし・アセンブリなし・ネイティブ依存なしの ピュアGo ONNX 推論パッケージ (A pure Go ONNX inference package — no cgo, no assembly, no native dependencies.)
Ultimate transpiler: converts Python to C++, Rust, C#, PowerShell, JavaScript, TypeScript, Dart, Go, Java, Swift, Kotlin, Ruby, Lua, Scala3, PHP, Nim, Julia, and Zig.
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
Text prompt-based voice quality designer using FlowMatching + GPT-SoVITS
Official PyTorch implementation of "Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator", CVPR 2026.
Official implementation of ArUco nano, a lightweight implementation of the ArUco marker detection algorithm up to 6.5x faster than standard OpenCV ArUco.
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
AI agents running research on single-GPU nanochat training automatically
GSV-TTS-Lite A high-performance inference engine specifically designed for the GPT-SoVITS text-to-speech model.(few shot voice cloning)
[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD
Extension module for Acoular for the realization of microphone array GUI applications with minimal programming effort.
This project uses Acoular to implement an acoustic camera for the miniDSP UMA-16 microphone array, with optional integration of transformer model.
AI Edge Quantizer: flexible post training quantization for LiteRT models.