MP-NeRF : Neural Radiance Fields for Dynamic Multi-person synthesis from Sparse Views

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Related Research Unit(s)


Original languageEnglish
Pages (from-to)317-325
Journal / PublicationComputer Graphics Forum
Issue number8
Publication statusPublished - Dec 2022


TitleACM SIGGRAPH / Eurographics Symposium of Computer Animation 2022
PlaceUnited Kingdom
Period13 - 15 September 2022


Multi-person novel view synthesis aims to generate free-viewpoint videos for dynamic scenes of multiple persons. However, current methods require numerous views to reconstruct a dynamic person and only achieve good performance when only a single person is present in the video. This paper aims to reconstruct a multi-person scene with fewer views, especially addressing the occlusion and interaction problems that appear in the multi-person scene. We propose MP-NeRF, a practical method for multi-person novel view synthesis from sparse cameras without the pre-scanned template human models. We apply a multi-person SMPL template as the identity and human motion prior. Then we build a global latent code to integrate the relative observations among multiple people, so we could represent multiple dynamic people into multiple neural radiance representations from sparse views. Experiments on multi-person dataset MVMP show that our method is superior to other state-of-the-art methods. © 2022 The Author(s). Computer Graphics Forum © 2022 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.

Research Area(s)

  • dynamic human, multi-person, view synthesis, volume rendering, 3d deep learning