Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction

TL;DR

This paper introduces AnchorUDF, a novel deep learning method for single-view 3D garment reconstruction that models open surfaces using unsigned distance functions and aligns gradient directions for improved accuracy.

Contribution

The paper proposes AnchorUDF, a new representation that combines pixel-aligned features with anchor points and gradient alignment to better reconstruct complex garments from a single image.

Findings

Achieves state-of-the-art results on MGN and Deep Fashion3D datasets.

Effectively models open garment surfaces with high resolution.

Improves projection accuracy through gradient direction alignment.

Abstract

While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details. In this paper, we propose a novel learnable Anchored Unsigned Distance Function (AnchorUDF) representation for 3D garment reconstruction from a single image. AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution. To capture diverse garment topologies, AnchorUDF not only computes pixel-aligned local image features of query points, but also leverages a set of anchor points located around the surface to enrich 3D position features for query points, which provides stronger 3D space context for the distance function. Furthermore, in order to obtain more accurate point projection direction at inference, we explicitly align the spatial gradient direction of AnchorUDF with the ground-truth direction to the surface during training. Extensive experiments on two public 3D garment datasets, i.e., MGN and Deep Fashion3D, demonstrate that AnchorUDF achieves the state-of-the-art performance on single-view garment reconstruction.