Multiple-Human Parsing in the Wild

Abstract

Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild. Existing works on human parsing mainly tackle single-person scenarios, which deviates from real-world applications where multiple persons are present simultaneously with interaction and occlusion. 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. The MHP dataset contains multiple persons captured in real-world scenes with pixel-level fine-grained semantic annotations in an instance-aware setting. The MH-Parser generates global parsing maps and person instance masks simultaneously in a bottom-up fashion with the help of a new Graph-GAN model. We envision that the MHP dataset will serve as a valuable data resource to develop new multi-human parsing models, and the MH-Parser offers a strong baseline to drive future research for multi-human parsing in the wild.

The first two authors are with equal contribution

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• A Structured Self-attentive Sentence Embedding
• Semantic Segmentation using Adversarial Networks
• Dynamic Graph Convolutional Networks
• Semantic Instance Segmentation with a Discriminative Loss Function
• Simultaneous Detection and Segmentation
• Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
• Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
• Fast Scene Understanding for Autonomous Driving
• Matching-CNN Meets KNN: Quasi-Parametric Human Parsing
• Holistic, Instance-Level Human Parsing
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network

Cited by in corpus (16)

• Devil in the Details: Towards Accurate Single and Multiple Human Parsing
• AIParsing: Anchor-free Instance-level Human Parsing
• Describe me if you can! Characterized Instance-level Human Parsing
• Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
• Keypoint Based Weakly Supervised Human Parsing
• Correlating Edge, Pose with Parsing
• Parsing R-CNN for Instance-Level Human Analysis
• Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing
• Renovating Parsing R-CNN for Accurate Multiple Human Parsing
• Quality-Aware Network for Human Parsing
• Human-centric Relation Segmentation: Dataset and Solution
• Graph-based Pyramid Global Context Reasoning with a Saliency-aware Projection for COVID-19 Lung Infections Segmentation
• An Autonomous Approach to Measure Social Distances and Hygienic Practices during COVID-19 Pandemic in Public Open Spaces
• End-to-end One-shot Human Parsing
• Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
• From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding