CVFeb 19

CORAL: Correspondence Alignment for Improved Virtual Try-On

arXiv:2602.17636v1h-index: 9
Originality Incremental advance
AI Analysis

This addresses a specific challenge in VTON for unpaired settings, offering an incremental improvement over existing methods.

The paper tackles the problem of preserving fine garment details in Virtual Try-On (VTON) by analyzing and improving person-garment correspondence in Diffusion Transformers, resulting in enhanced global shape transfer and local detail preservation.

Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required. These methods do not explicitly enforce person-garment alignment and fail to explain how correspondence emerges within Diffusion Transformers (DiTs). In this paper, we first analyze full 3D attention in DiT-based architecture and reveal that the person-garment correspondence critically depends on precise person-garment query-key matching within the full 3D attention. Building on this insight, we then introduce CORrespondence ALignment (CORAL), a DiT-based framework that explicitly aligns query-key matching with robust external correspondences. CORAL integrates two complementary components: a correspondence distillation loss that aligns reliable matches with person-garment attention, and an entropy minimization loss that sharpens the attention distribution. We further propose a VLM-based evaluation protocol to better reflect human preference. CORAL consistently improves over the baseline, enhancing both global shape transfer and local detail preservation. Extensive ablations validate our design choices.

Foundations

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

Your Notes