SLS4D: Sparse Latent Space for 4D Novel View Synthesis

TL;DR

This paper introduces SLS4D, a sparse latent space approach for 4D novel view synthesis that efficiently models dynamic scenes with significantly fewer parameters than existing methods.

Contribution

The paper proposes a novel sparse latent space representation for 4D scenes, capturing global dynamics efficiently and reducing model complexity compared to prior dense grid-based methods.

Findings

Achieves state-of-the-art 4D view synthesis quality.

Uses only about 6% of parameters compared to recent methods.

Effectively models global scene dynamics with sparse representations.

Abstract

Neural radiance field (NeRF) has achieved great success in novel view synthesis and 3D representation for static scenarios. Existing dynamic NeRFs usually exploit a locally dense grid to fit the deformation field; however, they fail to capture the global dynamics and concomitantly yield models of heavy parameters. We observe that the 4D space is inherently sparse. Firstly, the deformation field is sparse in spatial but dense in temporal due to the continuity of of motion. Secondly, the radiance field is only valid on the surface of the underlying scene, usually occupying a small fraction of the whole space. We thus propose to represent the 4D scene using a learnable sparse latent space, a.k.a. SLS4D. Specifically, SLS4D first uses dense learnable time slot features to depict the temporal space, from which the deformation field is fitted with linear multi-layer perceptions (MLP) to predict the displacement of a 3D position at any time. It then learns the spatial features of a 3D position using another sparse latent space. This is achieved by learning the adaptive weights of each latent code with the attention mechanism. Extensive experiments demonstrate the effectiveness of our SLS4D: it achieves the best 4D novel view synthesis using only about $6\%$ parameters of the most recent work.