We write your reusable computer vision tools. 💜
- computer-vision
- image-processing
- python
- yolo
Repository Index
81,588 visible repositories in the index
1–24 of 56 · Most stars
Graph Neural Network Library for PyTorch
- pytorch
- geometric-deep-learning
- graph-neural-networks
- deep-learning
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
🐍 Geometric Computer Vision Library for Spatial AI
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
- depth-estimation
- image-synthesis
- metric-depth-estimation
- monocular-depth-estimation
DUSt3R: Geometric 3D Vision Made Easy
TranslatedAI & parametric QR code generator. https://qrbtf.com
- qr
- qrcode
- generator
- qr-code
Simple Online Realtime Tracking with a Deep Association Metric
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
Most popular metrics used to evaluate object detection algorithms.
- metrics
- object-detection
- average-precision
- mean-average-precision
Torchreid: Deep learning person re-identification in PyTorch.
The Abstraction and Reasoning Corpus
- artificial-intelligence
- program-synthesis
- psychometrics
- intelligence-testing
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"
- computervision
- deeplearning
- 3d
- reconstruction
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
- open-reid
- pytorch
- person-reidentification
- image-retrieval
LPIPS metric. pip install lpips
- deep-learning
- deep-neural-networks
- perceptual
- perceptual-metric
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
- human-animation
- video-generation
- image-animatioln
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
- attention
- inference-acceleration
- llm
- quantization
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- 3d-reconstruction
- ai
- calibration
- depth-completion
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- point-cloud
- deep-learning
- classification
- segmentation
SymSpell: 1 million times faster spelling correction & fuzzy search through Symmetric Delete spelling correction algorithm
- levenshtein
- fuzzy-search
- approximate-string-matching
- edit-distance
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
- 3d-reconstruction
- depth-prediction
- feature-matching
- global-features
Accelerated deep learning R&D
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
- novel-view-synthesis
- surface-reconstruction
- gaussian-splatting