HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

TL;DR

HumanNeRF-SE introduces a simplified method combining explicit and implicit human representations to efficiently synthesize diverse human images in arbitrary poses, reducing complexity and improving generalization.

Contribution

It proposes a novel architecture that reduces parameters and training time while enhancing pose generalization by integrating explicit shape and rigid deformation with implicit representation.

Findings

Synthesizes images in arbitrary poses with few-shot input.

Speeds up image synthesis by 15 times without extra modules.

Outperforms state-of-the-art HumanNeRF with fewer parameters.

Abstract

We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these approaches by combining explicit and implicit human representations to design both generalized rigid deformation and specific non-rigid deformation. Our key insight is that explicit shape can reduce the sampling points used to fit implicit representation, and frozen blending weights from SMPL constructing a generalized rigid deformation can effectively avoid overfitting and improve pose generalization performance. Our architecture involving both explicit and implicit representation is simple yet effective. Experiments demonstrate our model can synthesize images under arbitrary poses with few-shot input and increase the speed of synthesizing images by 15 times through a reduction in computational complexity without using any existing acceleration modules. Compared to the state-of-the-art HumanNeRF studies, HumanNeRF-SE achieves better performance with fewer learnable parameters and less training time.