MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild

TL;DR

MultiPly is a novel framework that reconstructs multiple 3D human shapes from monocular in-the-wild videos, effectively disentangling individuals and capturing detailed shapes despite challenging interactions.

Contribution

It introduces a layered neural scene representation, hybrid segmentation, and confidence-guided optimization for accurate multi-person 3D reconstruction from monocular videos.

Findings

Outperforms prior methods on public datasets

Achieves temporally consistent 3D reconstructions

Handles close interactions and complex scenes effectively

Abstract

We present MultiPly, a novel framework to reconstruct multiple people in 3D from monocular in-the-wild videos. Reconstructing multiple individuals moving and interacting naturally from monocular in-the-wild videos poses a challenging task. Addressing it necessitates precise pixel-level disentanglement of individuals without any prior knowledge about the subjects. Moreover, it requires recovering intricate and complete 3D human shapes from short video sequences, intensifying the level of difficulty. To tackle these challenges, we first define a layered neural representation for the entire scene, composited by individual human and background models. We learn the layered neural representation from videos via our layer-wise differentiable volume rendering. This learning process is further enhanced by our hybrid instance segmentation approach which combines the self-supervised 3D segmentation and the promptable 2D segmentation module, yielding reliable instance segmentation supervision even under close human interaction. A confidence-guided optimization formulation is introduced to optimize the human poses and shape/appearance alternately. We incorporate effective objectives to refine human poses via photometric information and impose physically plausible constraints on human dynamics, leading to temporally consistent 3D reconstructions with high fidelity. The evaluation of our method shows the superiority over prior art on publicly available datasets and in-the-wild videos.