PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation

2020-01-07 · IEEE Access 2020 1 · Desen Zhou, Qian He

Human instance segmentation is a core problem for human-centric scene understanding and segmenting human instances poses a unique challenge to vision systems due to large intra-class variations in both appearance and shape, and complicated occlusion patterns. In this paper, we propose a new pose-aware human instance segmentation method. Compared to the previous pose-aware methods which first predict bottom-up poses and then estimate instance segmentation on top of predicted poses, our method integrates both top-down and bottom-up cues for an instance: it adopts detection results as human proposals and jointly estimates human pose and instance segmentation for each proposal. We develop a modular recurrent deep network that utilizes pose estimation to refine instance segmentation in an iterative manner. Our refinement modules exploit pose cues in two levels: as a coarse shape prior and local part attention. We evaluate our approach on two public multi-person benchmarks: OCHuman dataset and COCOPersons dataset. The proposed method surpasses the state-of-the-art methods on OCHuman dataset by 3.0 mAP and on COCOPersons by 6.4 mAP, demonstrating the effectiveness of our approach.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Human Instance Segmentation Instance Segmentation Pose Estimation Scene Understanding Segmentation Semantic Segmentation

TopoSeg: Topology-Aware Nuclear Instance Segmentation

2023-01-01 · ICCV 2023 1 · Hongliang He, Jun Wang, Pengxu Wei, Fan Xu 외

Nuclear instance segmentation has been critical for pathology image analysis in medical science, e.g., cancer diagnosis. Current methods typically adopt pixel-wise optimization for nuclei boundary exploration, where …

Instance Segmentation Segmentation Semantic Segmentation

PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation

2025-08-07 · Jingxuan He, Busheng Su, Finn Wong arxiv

Generating temporally coherent, long-duration videos with precise control over subject identity and movement remains a fundamental challenge for contemporary diffusion-based models, which often suffer from identity drift…

Video Generation

PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning

2022-07-07 · Shannan Guan, Haiyan Lu, Linchao Zhu, Gengfa Fang

3D pose estimation has recently gained substantial interests in computer vision domain. Existing 3D pose estimation methods have a strong reliance on large size well-annotated 3D pose datasets, and they suffer poor model…

3D Human Pose Estimation 3D Pose Estimation counterfactual Diversity+1

Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation

2023-04-24 · Soubarna Banik, Patricia Gschoßmann, Alejandro Mendoza Garcia, Alois Knoll

Occlusion is an omnipresent challenge in 3D human pose estimation (HPE). In spite of the large amount of research dedicated to 3D HPE, only a limited number of studies address the problem of occlusion explicitly. To fill…

3D Human Pose Estimation Data Augmentation Occlusion Handling Pose Estimation

PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF

2023-12-22 · Mohsen Gholami, Rabab Ward, Z. Jane Wang

This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in terms of human poses and camera viewpoints, large…

NeRF