Explore Projects
Discover 49 open source projects
Showing 21-40 of 49 projects
speedinghzl/CCNet
CCNet is a semantic segmentation library that uses Criss-Cross Attention to improve scene parsing performance.
cvg/pixel-perfect-sfm
A C++ library for pixel-perfect structure-from-motion with featuremetric refinement, awarded best student paper at ICCV 2021.
una-dinosauria/3d-pose-baseline
A simple baseline for 3D human pose estimation using TensorFlow, presented at ICCV 2017.
NJU-PCALab/STAR
An AI-powered video super-resolution model that enhances real-world videos using text-to-video generation.
NVlabs/describe-anything
An implementation for detailed localized image and video captioning using large multimodal models.
rese1f/StableVideo
StableVideo is a Python library for text-driven, consistency-aware diffusion-based video editing, presented at ICCV 2023.
piddnad/DDColor
A photo-realistic image colorization library using dual decoders, powered by PyTorch.
caiyuanhao1998/Retinexformer
One-stage Retinex-based Transformer for Low-light Image Enhancement
cszn/BSRGAN
BSRGAN is a PyTorch library for designing practical degradation models for deep blind image super-resolution.
bytedance/UNO
UNO is a universal customization method for both single and multi-subject image generation using diffusion models.
Walter0807/MotionBERT
A PyTorch implementation of MotionBERT, a unified approach for learning human motion representations.
torrvision/crfasrnn
This repository contains the source code for a semantic image segmentation method using Conditional Random Fields as Recurrent Neural Networks.
SHI-Labs/Versatile-Diffusion
A versatile diffusion model for text, image, and variation generation in a single model.
Sense-X/Co-DETR
Collaborative hybrid assignments training for DETRs, a novel object detection model.
wenqsun/DimensionX
A Python library for creating any 3D and 4D scenes from a single image with controllable video diffusion.
Pointcept/SegmentAnything3D
A tool for segmenting 3D objects in scenes using AI-powered computer vision techniques.
hustvl/VAD
A Python library for efficient autonomous driving using vectorized scene representation.
Fictionarry/ER-NeRF
Efficient Region-Aware Neural Radiance Fields for high-fidelity talking portrait synthesis
huanngzh/MV-Adapter
Official implementation of a multi-view consistent image generation model for AI-focused developers.
lightaime/deep_gcns_torch
A PyTorch library for Deep Graph Convolutional Networks (DeepGCNs) and other graph neural network models.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.