CVAug 11, 2021

M3D-VTON: A Monocular-to-3D Virtual Try-On Network

arXiv:2108.05126v183 citations
Originality Incremental advance
AI Analysis

This addresses the need for realistic 3D try-on in online shopping without requiring annotated 3D data, though it builds on prior 2D and 3D approaches.

The paper tackles the problem of 3D virtual try-on by proposing M3D-VTON, a network that reconstructs a 3D try-on mesh from a single person image and target clothing, achieving compelling details and improved efficiency over existing 3D methods.

Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value. However, existing 3D virtual try-on methods mainly rely on annotated 3D human shapes and garment templates, which hinders their applications in practical scenarios. 2D virtual try-on approaches provide a faster alternative to manipulate clothed humans, but lack the rich and realistic 3D representation. In this paper, we propose a novel Monocular-to-3D Virtual Try-On Network (M3D-VTON) that builds on the merits of both 2D and 3D approaches. By integrating 2D information efficiently and learning a mapping that lifts the 2D representation to 3D, we make the first attempt to reconstruct a 3D try-on mesh only taking the target clothing and a person image as inputs. The proposed M3D-VTON includes three modules: 1) The Monocular Prediction Module (MPM) that estimates an initial full-body depth map and accomplishes 2D clothes-person alignment through a novel two-stage warping procedure; 2) The Depth Refinement Module (DRM) that refines the initial body depth to produce more detailed pleat and face characteristics; 3) The Texture Fusion Module (TFM) that fuses the warped clothing with the non-target body part to refine the results. We also construct a high-quality synthesized Monocular-to-3D virtual try-on dataset, in which each person image is associated with a front and a back depth map. Extensive experiments demonstrate that the proposed M3D-VTON can manipulate and reconstruct the 3D human body wearing the given clothing with compelling details and is more efficient than other 3D approaches.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes