GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis

TL;DR

GenLayNeRF introduces a novel, generalizable layered scene representation for multi-human view synthesis that aligns 3D models with input views without per-scene optimization, enabling high-quality free-viewpoint rendering from sparse views.

Contribution

It proposes a fully trainable, multi-human layered scene model with pixel-level 3D model alignment, eliminating the need for per-scene optimization and handling sparse views effectively.

Findings

Outperforms existing generalizable and non-human NeRF methods.

Achieves comparable results to layered per-scene methods without test-time optimization.

Effectively handles multi-human scenes with sparse input views.

Abstract

Novel view synthesis (NVS) of multi-human scenes imposes challenges due to the complex inter-human occlusions. Layered representations handle the complexities by dividing the scene into multi-layered radiance fields, however, they are mainly constrained to per-scene optimization making them inefficient. Generalizable human view synthesis methods combine the pre-fitted 3D human meshes with image features to reach generalization, yet they are mainly designed to operate on single-human scenes. Another drawback is the reliance on multi-step optimization techniques for parametric pre-fitting of the 3D body models that suffer from misalignment with the images in sparse view settings causing hallucinations in synthesized views. In this work, we propose, GenLayNeRF, a generalizable layered scene representation for free-viewpoint rendering of multiple human subjects which requires no per-scene optimization and very sparse views as input. We divide the scene into multi-human layers anchored by the 3D body meshes. We then ensure pixel-level alignment of the body models with the input views through a novel end-to-end trainable module that carries out iterative parametric correction coupled with multi-view feature fusion to produce aligned 3D models. For NVS, we extract point-wise image-aligned and human-anchored features which are correlated and fused using self-attention and cross-attention modules. We augment low-level RGB values into the features with an attention-based RGB fusion module. To evaluate our approach, we construct two multi-human view synthesis datasets; DeepMultiSyn and ZJU-MultiHuman. The results indicate that our proposed approach outperforms generalizable and non-human per-scene NeRF methods while performing at par with layered per-scene methods without test time optimization.