Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images
This addresses a bottleneck in 3D content creation pipelines by enabling high-quality digital assets from single images, though it is incremental as it builds on implicit shape learning.
The paper tackles the problem of reconstructing topology-consistent, separated garment meshes from single images, which existing implicit methods fail to produce, and demonstrates that their method outperforms counterparts in layered garment reconstruction.
Fueled by the power of deep learning techniques and implicit shape learning, recent advances in single-image human digitalization have reached unprecedented accuracy and could recover fine-grained surface details such as garment wrinkles. However, a common problem for the implicit-based methods is that they cannot produce separated and topology-consistent mesh for each garment piece, which is crucial for the current 3D content creation pipeline. To address this issue, we proposed a novel geometry inference framework ReEF that reconstructs topology-consistent layered garment mesh by registering the explicit garment template to the whole-body implicit fields predicted from single images. Experiments demonstrate that our method notably outperforms its counterparts on single-image layered garment reconstruction and could bring high-quality digital assets for further content creation.