Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.

DexiNed: Dense EXtreme Inception Network for Edge Detection

[CVPR2024] The official implementation of "MoCha-Stereo: Motif Channel Attention Network for Stereo Matching”.

Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"

DUSt3R: Geometric 3D Vision Made Easy

[CVPR 2023] DynamicStereo: Consistent Dynamic Depth from Stereo Videos.

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Metric depth estimation from a single image and referring segmentation

[IEEE T-PAMI] All you need for End-to-end Autonomous Driving

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"

Code release for NeRF (Neural Radiance Fields)

An open autonomous driving platform

[CVPR 2024] DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

[CVPR 2023] Domain Generalized Stereo Matching via Hierarchical Visual Transformation

[IROS 2023] TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

[ICCV 2023] OccNet: Scene as Occupancy

Implementation of popular deep learning networks with TensorRT network definition API

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet