textcunma
Follow
Stars
[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation
MPEG encoder and decoder framework that showcases many image processing techniques; namely frame sub/up-sampling, image/video compression, and motion estimation.
A new framework for creating desktop apps from websites, using system installed browsers and NodeJS
An official code release of the paper RGB no more: Minimally Decoded JPEG Vision Transformers
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Automatic generation of picture undercoat from line drawings
This Python library makes it easy to display images and videos in a notebook.
collections of data science, machine learning and data visualization projects with pandas, sklearn, matplotlib, tensorflow2, Keras, various ML algorithms like random forest classifier, boosting, etc
4DHumans: Reconstructing and Tracking Humans with Transformers
Fast neural radiance field training with free camera trajectories
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
A curated list of awesome self-supervised methods
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
This is a code repository for pytorch c++ (or libtorch) tutorial.
A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.
Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
処理の検証や比較検討での用途を想定したノードエディターベースの画像処理アプリ(A node editor-based image processing application intended for use in processing verification and comparison studies)
Code release for ConvNeXt V2 model
Ray Tracing in One Weekend (RTOW) in Cuda with a GLFW live render display
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
The official Open-Asset-Importer-Library Repository. Loads 40+ 3D-file-formats into one unified and clean data structure.
Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies