Abstract
Regression-based 3D human pose and shape estimation often fall into one of two different paradigms. Parametric approaches, which regress the parameters of a human body model, tend to produce physically plausible but image-mesh misalignment results. In contrast, non-parametric approaches directly regress human mesh vertices, resulting in pixel-aligned but unreasonable predictions. In this paper, we consider these two paradigms together for a better overall estimation. To this end, we propose a novel HYbrid REgressor (HYRE) that greatly benefits from the joint learning of both paradigms. The core of our HYRE is a hybrid intermediary across paradigms that provides complementary clues to each paradigm at the shared feature level and fuses their results at the part-based decision level, thereby bridging the gap between the two. We demonstrate the effectiveness of the proposed method through both quantitative and qualitative experimental analyses, resulting in improvements for each approach and ultimately leading to better hybrid results. Our experiments show that HYRE outperforms previous methods on challenging 3D human pose and shape benchmarks.
Funding Information
  • National Natural Science Foundation of China (62373009)
  • Natural Science Foundation of Guangdong Province (2024A1515012089)
  • Natural Science Foundation of Shenzhen (JCYJ20230807120801002)
  • Shenzhen Innovation in Science and Technology Foundation for The Excellent Youth Scholars (RCYX20231211090248064)
  • Interdisciplinary Doctoral Grant from the Personalized Health and Related Technologies (PHRT) of ETH Domain, Switzerland (iDoc 2021-360)
  • European Union’s Horizon Europe research and innovation program (101120237 (ELIAS))
  • PNRR Project Future AI Research
  • NRRP MUR program funded by the NextGenerationEU (PE00000013)