AdaptSegNet alternatives for AI agents.

OpenMMLab Foundational Library for Training Deep Learning Models

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

An open-source framework for training large multimodal models.

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Open Machine Learning course

3D ResNets for Action Recognition (CVPR 2018)

PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.

Automatically remove the mosaics in images and videos, or add mosaics to them.

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Gated-Shape CNN for Semantic Segmentation (ICCV 2019)

Scenic: A Jax Library for Computer Vision Research and Beyond

A python library for self-supervised learning on images.

Demo for the "Talking Head Anime from a Single Image."

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

An open source library and framework for deep learning on satellite and aerial imagery.