Search papers, labs, and topics across Lattice.
This paper introduces a novel task in e-commerce called Fashion Detail Generation, focusing on generating photorealistic close-up views of specific garment details based on reference images. The authors present FDBench, a benchmark with over 40,000 human-verified detail pairs, to address the semantic gap in aligning focus markers with corresponding details. Utilizing Cross-modal Feature Alignment Distillation (CFAD) and a consistency reward model, the proposed method, DetailAnywhere, outperforms existing state-of-the-art techniques in both quantitative metrics and qualitative human evaluations.
Bridging the semantic gap in fashion detail generation, DetailAnywhere sets a new standard by significantly outperforming existing methods in producing high-quality garment close-ups.
Diffusion-based generative AI has achieved remarkable success in e-commerce applications such as virtual try-on, poster generation, and product background synthesis. However, when making online purchasing decisions for apparel, consumers also desire the freedom to examine specific detail regions of interest, such as collars, cuffs, and fabric textures, yet existing methods have not explicitly studied this setting. We therefore formalize a new, non-template task: Fashion Detail Generation with focus conditioning, and release FDBench, the first benchmark comprising 40K+ human-verified reference-detail pairs across 41 different categories. This task poses a unique semantic gap challenge: the model must bridge the correspondence between a focus marker on a product reference image and a photorealistic close-up view of the indicated region, while faithfully preserving the garment's identity, without any precise prompt. To bridge this gap, we propose Cross-modal Feature Alignment Distillation (CFAD), which leverages a fine-tuned DINOv3 teacher to align both branches of a Multimodal Diffusion Transformer in a shared semantic space via dual-branch distillation. To further improve consistency between generated details and reference images, we introduce a consistency reward model that jointly scores image pairs along three quality axes and optimizes generation via reinforcement learning. Experiments show that our model DetailAnywhere significantly outperforms all state-of-the-art opensource methods across all metrics and human evaluations.
