“computer-vision” 相关开源项目

Local-first video knowledge base that indexes your videos with transcription, frame analysis and embeddings, then lets you search scenes in natural language.

Research code for WorldGrow, a method that generates open-ended, walkable explicit 3D worlds block by block from a seed block.

A collection of 419 pre-trained AI models covering vision, speech, NLP, and LLMs, each runnable from a simple CLI with automatic weight download.

基于码本查找 Transformer 的盲人脸修复工具，可增强模糊、低质量或受损的人脸图像与视频。