brandpose
Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)
- 210
- Python
- MIT
- 3 wk ago
Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)
This repository is forked from shouxieai/tensorRT_Pro, extending it to support a wide range of vision models with high-performance TensorRT C++ inference.
[CVPR 2026] OccAny: Generalized Unconstrained Urban 3D Occupancy. The first Unified Framework for Generalized 3D Occupancy Prediction. Supports SAM2/SAM3, MUSt3R & Depth Anything 3.
ReShot — copy the shot, not the actors. Video → depth map, OpenPose skeleton or canny lines for Seedance 2.0/2.5 reference video, MiniMax H3 Fun ControlNet and Wan VACE. Apache-2.0. Open-sourced by Maosika 猫斯卡 (www.maosika.com), the AI short-drama production system.
Depth map to normal map: a CLI, a portable ONNX graph, and a browser demo. No depth map? It estimates one from a photograph.
An Android app running inference on Depth-Anything and Depth-Anything-V2
AI-KSK Qwen Image 2.1 Creator Skill v3.0.0 - a reusable Codex skill for Qwen Image 2.1 creation, editing, ControlNet Union and ComfyUI workflow engineering, with Python standard-library validators.