Real-Time Semantic Segmentation

77 papers with code • 8 benchmarks • 12 datasets

Semantic Segmentation is a computer vision task that involves assigning a semantic label to each pixel in an image. In Real-Time Semantic Segmentation, the goal is to perform this labeling quickly and accurately in real-time, allowing for the segmentation results to be used for tasks such as object recognition, scene understanding, and autonomous navigation.

( Image credit: TorchSeg )


Use these libraries to find Real-Time Semantic Segmentation models and implementations
16 papers
14 papers
4 papers
See all 9 libraries.

Most implemented papers

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

PaddlePaddle/PaddleSeg 2 Nov 2015

We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.

Pyramid Scene Parsing Network

hszhao/PSPNet CVPR 2017

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

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

PaddlePaddle/PaddleSeg 7 Jun 2016

The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications.

Fully Convolutional Networks for Semantic Segmentation

pytorch/vision CVPR 2015

Convolutional networks are powerful visual models that yield hierarchies of features.

HarDNet: A Low Memory Traffic Network

PingoLH/Pytorch-HarDNet ICCV 2019

We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic.

Fast-SCNN: Fast Semantic Segmentation Network

PaddlePaddle/PaddleSeg 12 Feb 2019

The encoder-decoder framework is state-of-the-art for offline semantic image segmentation.

SOLOv2: Dynamic and Fast Instance Segmentation

WXinlong/SOLO NeurIPS 2020

Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

PaddlePaddle/PaddleSeg ECCV 2018

Semantic segmentation requires both rich spatial information and sizeable receptive field.

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

hszhao/ICNet ECCV 2018

We focus on the challenging task of real-time semantic segmentation in this paper.

Lite-HRNet: A Lightweight High-Resolution Network

HRNet/Lite-HRNet CVPR 2021

We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.