A Unified Toolkit for Deep Learning Based Document Image Analysis

(CVPR 2021 Oral) Open World Object Detection

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

This repo is implemented based on detectron2 and centernet

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

A fork of Detectron2 with ResNeSt backbone

[CVPR 2020] VoVNet backbone networks for detectron2

[CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)

Deploy Computer Vision solutions with a few lines of code.

detectron2 windows build

detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn

[ECCV 2020] Boundary-preserving Mask R-CNN

Python package for automatic tree crown delineation based on the Detectron2 implementation of Mask R-CNN

Detectron2 for Document Layout Analysis

Instance Shadow Detection (CVPR 2020)

Official code of ECCV 2020 paper "GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision". GSNet performs joint vehicle pose estimation and vehicle shape reconstruction with single RGB image as input.

Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val