Animatable Human Rendering from Monocular Video via Pose-Independent Deformation

Tong Duan, Zekai Jiang, Zipei Ma, Dongyu Zhang

Abstract: Rendering animatable avatars from monocular videos has significant applications in the broader field of interactive entertainment. Previous methods based on Neural Radiance Field (NeRF) struggle with long training time and tend to overfit on seen poses. To address this, we introduce PID-NeRF, a novel framework with a Pose-Independent Deformation (PID) module. Specifically, PID module learns a multi-entity shared skinning prior and optimizes instance-level non-rigid offsets in UV-H space, which is independent of human motion. The pose-independence enable our model unify the backward and forward human skeleton deformations in same network parameters, increasing the generalizability of our skinning prior. Additionally, a bounded segment modeling (BSM) strategy is utilized with a window function to smooth overlapping regions of bounding boxes, to balance the training speed and rendering quality. Extensive experiments demonstrate that our method achieves better results than the state-of- the-art methods in novel-view and novel-pose synthesis on multiple datasets.