Human Parsing

38 papers with code • 1 benchmarks • 2 datasets

Human parsing is the task of segmenting a human image into different fine-grained semantic parts such as head, torso, arms and legs.

( Image credit: Multi-Human-Parsing (MHP) )

Most implemented papers

Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark

Engineering-Course/LIP_JPPNet 5 Apr 2018

To further explore and take advantage of the semantic correlation of these two tasks, we propose a novel joint human parsing and pose estimation network to explore efficient context modeling, which can simultaneously predict parsing and pose with extremely high quality.

CCNet: Criss-Cross Attention for Semantic Segmentation

speedinghzl/CCNet ICCV 2019

Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.

Multiple-Human Parsing in the Wild

ZhaoJ9014/Multi-Human-Parsing_MHP 19 May 2017

To address the multi-human parsing problem, we introduce a new multi-human parsing (MHP) dataset and a novel multi-human parsing model named MH-Parser.

Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing

open-mmlab/mmpose 10 Apr 2018

Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis, person re-identification and autonomous driving, etc.

Devil in the Details: Towards Accurate Single and Multiple Human Parsing

liutinglt/CE2P 17 Sep 2018

Human parsing has received considerable interest due to its wide application potentials.

Parsing R-CNN for Instance-Level Human Analysis

soeaver/Parsing-R-CNN CVPR 2019

Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance.

Self-Correction for Human Parsing

PeikeLi/Self-Correction-Human-Parsing 22 Oct 2019

To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models.

Learning from Synthetic Animals

JitengMu/Learning-from-Synthetic-Animals CVPR 2020

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data.

Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer

Gaoyiminggithub/Graphonomy-Panoptic 26 Jan 2021

Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e. g., sharing discrepant label granularity) without extensive re-training.

Text2Human: Text-Driven Controllable Human Image Generation

yumingj/Text2Human 31 May 2022

In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation.