A Python high-performance screen capture library for Windows using Desktop Duplication API
Repositories
nagadomi repositories
Depth Anything 3
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Ruby wrapper for KyTea
Pythonic bindings for FFmpeg's libraries.
TexTools is a UV and Texture tool set for 3dsMax created several years ago. This open repository will port in time several of the UV tools to Blender in python. For more information on TexTool's tools and features see: http://renderhjs.net/textools/blender
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Metric depth estimation from a single image
Face and Landmark Detector for Anime/Manga. This is 2009s version of Imager::AnimeFace, but it works on recent system.
Japanese word segmenter
mmd_tools is a blender addon for importing Models and Motions of MikuMikuDance.
Caffe: a fast open framework for deep learning.
CMake build scripts to automate building the Caffe library and its dependencies.
Convert torch t7 model to pytorch model and source.
Torch-7 FFI bindings for NVIDIA CuDNN
A CUDA backend for Torch7
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO