Skip to yearly menu bar Skip to main content


Poster

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

Caoyuan Ma · Yu-Lun Liu · Zhixiang Wang · Wu Liu · Xinchen Liu · Zheng Wang

Arch 4A-E Poster #126
[ ] [ Paper PDF ]
[ Poster
Wed 19 Jun 10:30 a.m. PDT — noon PDT

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.

Chat is not available.