Explore Projects
Discover 159 open source projects
Showing 61-80 of 159 projects
NVlabs/PWC-Net
A PyTorch implementation of the PWC-Net, a CNN-based optical flow estimation model for computer vision tasks.
SHI-Labs/OneFormer
A powerful universal image segmentation model that can handle various segmentation tasks with a single transformer-based model.
Pointcept/PointTransformerV3
Official repository of Point Transformer V3 (PTv3), a computer vision AI model for point cloud processing.
williamyang1991/DualStyleGAN
Generates high-resolution portrait style transfer using the Dual StyleGAN model.
franciszzj/Leffa
This is a Python library for learning flow fields in attention for controllable person image generation.
Picsart-AI-Research/StreamingT2V
Generates long videos from text using a consistent and dynamic approach.
ZiqiaoPeng/SyncTalk
An official paper from CVPR 2024 on a talking head synthesis model that focuses on audio-driven synchronization.
jiupinjia/stylized-neural-painting
Stylized Neural Painting is a PyTorch implementation for neural-based image stylization and painting translation.
yoshitomo-matsubara/torchdistill
A PyTorch-based framework for reproducible deep learning studies with 26 knowledge distillation methods.
niessner/BundleFusion
A real-time globally consistent 3D reconstruction library using online surface re-integration.
Kobaayyy/Awesome-CVPR2026-CVPR2025-CVPR2024-CVPR2021-CVPR2020-Low-Level-Vision
A collection of papers and code for CVPR conferences focused on low-level computer vision tasks.
cvg/nice-slam
NICE-SLAM is a neural implicit approach for scalable 3D reconstruction and localization.
verlab/accelerated_features
Fast and robust local feature extraction for image processing and computer vision applications.
FoundationVision/Infinity
A high-performance, autoregressive model for generating high-resolution images from text prompts.
opendatalab/OmniDocBench
A comprehensive benchmark for document parsing and evaluation, designed for CVPR 2025.
facebookresearch/fast3r
Fast3R is a Python library for 3D reconstruction from a large number of images in a single forward pass.
Tencent/DepthCrafter
DepthCrafter is a Python library that generates consistent long depth sequences for open-world videos using AI.
autonomousvision/transfuser
A Transformer-based sensor fusion model for end-to-end autonomous driving.
IDEA-Research/MaskDINO
Official implementation of a paper on a unified Transformer-based framework for object detection and segmentation.
pq-yang/MatAnyone
This is an AI-powered video matting library that provides stable and consistent video segmentation.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.