# RepParser: End-to-End Multiple Human Parsing with Representative Parts

arXiv: https://arxiv.org/abs/2208.12908 · HTML: https://mlsanity.com/paper/2208.12908/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 27 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Instance-level Human Parsing via Part Grouping Network](https://mlsanity.com/paper/1808.00157/) (2018)
- [Fully Convolutional Networks for Panoptic Segmentation](https://mlsanity.com/paper/2012.00720/) (2020)
- [Graphonomy: Universal Human Parsing via Graph Transfer Learning](https://mlsanity.com/paper/1904.04536/) (2019)
- [Devil in the Details: Towards Accurate Single and Multiple Human Parsing](https://mlsanity.com/paper/1809.05996/) (2018)
- [Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing](https://mlsanity.com/paper/1804.03287/) (2018)
- [Parsing R-CNN for Instance-Level Human Analysis](https://mlsanity.com/paper/1811.12596/) (2018)
- [Renovating Parsing R-CNN for Accurate Multiple Human Parsing](https://mlsanity.com/paper/2009.09447/) (2020)
- [FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions](https://mlsanity.com/paper/2105.14185/) (2021)
- [Learning Semantic Neural Tree for Human Parsing](https://mlsanity.com/paper/1912.09622/) (2019)
- [SOIT: Segmenting Objects with Instance-Aware Transformers](https://mlsanity.com/paper/2112.11037/) (2021)
- [Progressive One-shot Human Parsing](https://mlsanity.com/paper/2012.11810/) (2020)
- [KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences](https://mlsanity.com/paper/2206.10090/) (2022)

## Built on by (most cited first, 3 of 3)

- [3D Segmentation of Humans in Point Clouds with Synthetic Data](https://mlsanity.com/paper/2212.00786/) (2022)
- [UniParser: Multi-Human Parsing with Unified Correlation Representation Learning](https://mlsanity.com/paper/2310.08984/) (2023)
- [CIParsing: Unifying Causality Properties into Multiple Human Parsing](https://mlsanity.com/paper/2308.12218/) (2023)

## Abstract (arXiv)

Existing methods of multiple human parsing usually adopt a two-stage strategy (typically top-down and bottom-up), which suffers from either strong dependence on prior detection or highly computational redundancy during post-grouping. In this work, we present an end-to-end multiple human parsing framework using representative parts, termed RepParser. Different from mainstream methods, RepParser solves the multiple human parsing in a new single-stage manner without resorting to person detection or post-grouping.To this end, RepParser decouples the parsing pipeline into instance-aware kernel generation and part-aware human parsing, which are responsible for instance separation and instance-specific part segmentation, respectively. In particular, we empower the parsing pipeline by representative parts, since they are characterized by instance-aware keypoints and can be utilized to dynamically parse each person instance. Specifically, representative parts are obtained by jointly localizing centers of instances and estimating keypoints of body part regions. After that, we dynamically predict instance-aware convolution kernels through representative parts, thus encoding person-part context into each kernel responsible for casting an image feature as an instance-specific representation.Furthermore, a multi-branch structure is adopted to divide each instance-specific representation into several part-aware representations for separate part segmentation.In this way, RepParser accordingly focuses on person instances with the guidance of representative parts and directly outputs parsing results for each person instance, thus eliminating the requirement of the prior detection or post-grouping.Extensive experiments on two challenging benchmarks demonstrate that our proposed RepParser is a simple yet effective framework and achieves very competitive performance.