3D human pose and shape estimation via de-occlusion multi-task learning

Ran, Hang (author): Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China

Ning, Xin (author): Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China; Cognitive Computing Technology Joint Laboratory, Wave Group, Beijing, China

Li, Weijun (author): Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China; Beijing Key Laboratory Of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China

Hao, Meilan (author): Chinese Academy of Sciences, Beijing, China; Hebei University of Engineering, Handan, China

Tiwari, Prayag, 1991- (author): Högskolan i Halmstad,Akademin för informationsteknologi

(creator_code:org_t)

Amsterdam : Elsevier, 2023
2023
English.
In: Neurocomputing. - Amsterdam : Elsevier. - 0925-2312 .- 1872-8286. ; 548

Related links:: https://urn.kb.se/re...; show more...; https://doi.org/10.1...; show less...

Abstract Subject headings

Three-dimensional human pose and shape estimation is to compute a full human 3D mesh given a single image. The contamination of features caused by occlusion usually degrades its performance significantly. Recent progress in this field typically addressed the occlusion problem implicitly. By contrast, in this paper, we address it explicitly using a simple yet effective de-occlusion multi-task learning network. Our key insight is that feature for mesh parameter regression should be noiseless. Thus, in the feature space, our method disentangles the occludee that represents the noiseless human feature from the occluder. Specifically, a spatial regularization and an attention mechanism are imposed in the backbone of our network to disentangle the features into different channels. Furthermore, two segmentation tasks are proposed to supervise the de-occlusion process. The final mesh model is regressed by the disentangled occlusion-aware features. Experiments on both occlusion and non-occlusion datasets are conducted, and the results prove that our method is superior to the state-of-the-art methods on two occlusion datasets, while achieving competitive performance on a non-occlusion dataset. We also demonstrate that the proposed de-occlusion strategy is the main factor to improve the robustness against occlusion. The code is available at https://github.com/qihangran/De-occlusion_MTL_HMR. © 2023

By the author/editor: Ran, Hang; Ning, Xin; Li, Weijun; Hao, Meilan; Tiwari, Prayag, ...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.