Logo image
Back
Conditional plane-based multi-scene representation for novel view synthesis
Journal article   Open access   Peer reviewed

Conditional plane-based multi-scene representation for novel view synthesis

Uchitha Rajapaksha, Hamid Laga, Dean Diepeveen, Mohammed Bennamoun and Ferdous Sohel
Neurocomputing (Amsterdam), Vol.657, 131657
2025
DOI: https://doi.org/10.1016/j.neucom.2025.131657
Appears in  Open Access via Read & Publish Agreements
pdf
Published6.07 MBDownloadView
CC BY V4.0,  Open Access

Abstract

Existing explicit and implicit-explicit hybrid neural representations for novel view synthesis are scene-specific. In other words, they represent only a single scene and require retraining for every novel scene. Implicit scene-agnostic methods rely on large multilayer perception (MLP) networks conditioned on learned features. They are computationally expensive during training and rendering times. In contrast, we propose a novel plane-based representation that learns to represent multiple static and dynamic scenes during training and renders per-scene novel views during inference. The method consists of a deformation network, explicit feature planes, and a conditional decoder. Explicit feature planes are used to represent a time-stamped view space volume and a shared canonical volume across multiple scenes. The deformation network learns the deformations across shared canonical object space and time-stamped view space. The conditional decoder estimates the color and density of each scene constrained by a scene-specific latent code. We evaluated and compared the performance of the proposed representation on static (NeRF) and dynamic (Plenoptic videos) datasets. The results show that explicit planes combined with tiny MLPs can efficiently train multiple scenes simultaneously. The project page: https://anonpubcv.github.io/cplanes/.

Details

Metrics

4 Record Views
Logo image