Scene Parsing

66 papers with code • 2 benchmarks • 4 datasets

Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. MIT Description


Use these libraries to find Scene Parsing models and implementations

Most implemented papers

Pyramid Scene Parsing Network

hszhao/PSPNet CVPR 2017

Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.

Semantic Understanding of Scenes through the ADE20K Dataset

CSAILVision/semantic-segmentation-pytorch 18 Aug 2016

Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision.

OCNet: Object Context Network for Scene Parsing

PkuRainBow/OCNet 4 Sep 2018

To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling~\citep{zhao2017pyramid} and atrous spatial pyramid pooling~\citep{chen2018deeplab}.

ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data

Nguyendat-bit/U-net 1 Apr 2019

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications.

Panoptic Segmentation

cocodataset/panopticapi CVPR 2019

We propose and study a task we name panoptic segmentation (PS).

Semantic Flow for Fast and Accurate Scene Parsing

donnyyou/torchcv ECCV 2020

A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.

Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes

ydhongHIT/DDRNet 15 Jan 2021

The proposed deep dual-resolution networks (DDRNets) are composed of two deep branches between which multiple bilateral fusions are performed.

PSANet: Point-wise Spatial Attention Network for Scene Parsing

hszhao/PSANet ECCV 2018

We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition

iduta/pyconv 20 Jun 2020

This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.

Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing

MartinHahner88/FoggySynscapes 19 Oct 2018

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis.