cityscapes-dataset

This is the official repository for our recent work: PIDNet

A pytorch-based real-time segmentation model for autonomous driving

Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]

Cityscapes to CoCo Format Conversion Tool for Mask-RCNN and Detectron

A Pytorch implementation of CASENet for the Cityscapes Dataset

Detectron2 implementation of DA-Faster R-CNN, Domain Adaptive Faster R-CNN for Object Detection in the Wild, Computer Vision and Pattern Recognition (CVPR) 2018

Official Detectron2 implementation of DA-RetinaNet, An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites, Image and Vision Computing (IMAVIS) 2021

Repository for "Stochastic Segmentation with Conditional Categorical Diffusion Models" (ICCV 2023)

【X世纪星际终端】A Wechat Social and AR Game: 基于微信聊天，结合增强现实技术AR+LBS（基于图像位置）的轻社交星际漂流瓶游戏。向外太空发送漂流信息，看看AI预测的外星人是长什么样的，寻找身边的外星人,逗逗外星生物，看看外星植物及外星建筑。Send the message to the outer space, find the aliens in the earth. Let`s see what they look like from LSGAN`s prediction. Also, Have a look at the aliens' pets and the vegetation from the outer space

Official re-implementation of the Calibrated Adversarial Refinement model described in the paper "Calibrated Adversarial Refinement for Stochastic Semantic Segmentation"

[ICIP 2019] : Official PyTorch implementation of the paper "What's There in The Dark" accepted in IEEE International Conference in Image Processing 2019 (ICIP19) , Taipei, Taiwan.

CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation (ICRA2021)

Official Repository for BEVANet: Bilateral Efficient Visual Attention Network for Real-time Semantic Segmentation (ICIP 2025 Spotlight Oral)

Official implementation of Inconsistency Masks. A robust semi-supervised segmentation framework that reframes model disagreement as a signal for uncertainty filtering. It acts as a general performance enhancer for SOTA models and a stabilizer for training from scratch.

Implementation of the Instance Stixel pipeline. Paper:

Collection of scripts for preparation of datasets for semantic segmentation of UAV images

PyTorch implementation for Semantic Segmentation on Cityscapes dataset using R2UNET and its modified version.

GPU-accelerated Semantic Image Segmentation with PyTorch

Python program to visualize Deeplab (trained on Cityscapes dataset) results.