Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning

Wenpeng Xing, Jie Chen*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

3 Citations (Scopus)


Novel view synthesis of static scenes has achieved remarkable advancements in producing photo-realistic results. However, key challenges remain for immersive rendering of dynamic scenes. One of the seminal image-based rendering method, the multi-plane image (MPI), produces high novel-view synthesis quality for static scenes. But modelling dynamic contents by MPI is not studied. In this paper, we propose a novel Temporal-MPI representation which is able to encode the rich 3D and dynamic variation information throughout the entire video as compact temporal basis and coefficients jointly learned. Time-instance MPI for rendering can be generated efficiently using mini-seconds by linear combinations of temporal basis and coefficients from Temporal-MPI. Thus novel-views at arbitrary time-instance will be able to be rendered via Temporal-MPI in real-time with high visual quality. Our method is trained and evaluated on Nvidia Dynamic Scene Dataset. We show that our proposed Temporal-MPI is much faster and more compact compared with other state-of-the-art dynamic scene modelling methods.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2022
Subtitle of host publication17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XV
EditorsShai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner
PublisherSpringer Cham
Number of pages16
ISBN (Electronic)9783031197840
ISBN (Print)9783031197833
Publication statusPublished - 31 Oct 2022
EventEuropean Conference on Computer Vision, ECCV 2022 - Tel Aviv, Israel
Duration: 23 Oct 202227 Oct 2022


ConferenceEuropean Conference on Computer Vision, ECCV 2022
CityTel Aviv
Internet address

User-Defined Keywords

  • Multi-plane image
  • Neural basis learning
  • Novel view synthesis

Cite this