D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

TL;DR

This paper introduces an uncertainty-aware implicit distribution approach for human digitization, improving 3D clothed human reconstruction by modeling uncertainty based on proximity to the surface, leading to more realistic details.

Contribution

It proposes replacing deterministic implicit values with an adaptive uncertainty distribution to enhance 3D human reconstruction accuracy and realism.

Findings

Significant improvements on baseline models.

Enhanced capture of wrinkles and limb details.

Better differentiation of points near the surface.

Abstract

Realistic virtual humans play a crucial role in numerous industries, such as metaverse, intelligent healthcare, and self-driving simulation. But creating them on a large scale with high levels of realism remains a challenge. The utilization of deep implicit function sparks a new era of image-based 3D clothed human reconstruction, enabling pixel-aligned shape recovery with fine details. Subsequently, the vast majority of works locate the surface by regressing the deterministic implicit value for each point. However, should all points be treated equally regardless of their proximity to the surface? In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface. This simple ``value to distribution'' transition yields significant improvements on nearly all the baselines. Furthermore, qualitative results demonstrate that the models trained using our uncertainty distribution loss, can capture more intricate wrinkles, and realistic limbs. Code and models are available for research purposes at https://github.com/psyai-net/D-IF_release.