[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

AvitoTech team playbook

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

Real-Time DEtection TRansformer. Like original repo, but with package-ready pytorch version.

The open-source tool for building high-quality datasets and computer vision models

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

Open Source Differentiable Computer Vision Library

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

Official open source SVG icon library for Bootstrap.

Тестовое задание по 3D ML

Two-stage CenterNet trained on SynthText. Model and output examples available at https://disk.yandex.ru/d/s0Kvl-NAtyRGkw

An open letter in support of Richard Matthew Stallman being reinstated by the Free Software Foundation

R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object

This is the source code of the feasibility study for Autoware architecture proposal.

A PyTorch implementation of "ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection"

Ultimate posts for opendatascience telegram channel

The devkit of the nuScenes dataset.

Convert darknet weights to caffemodel