arXiv AI
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Aug 25
Grounding Free-Form Instructions for Fashion Complementary Image Generation
arXiv:2608.23302v1 Announce Type: new Abstract: Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural mul...
Hugging Face Trending Papers
Aug 24
Grounding Free-Form Instructions for Fashion Complementary Image Generation
Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural multimodal grounding problem where models must inter...
arXiv AI
Jun 18
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
arXiv:2606. 19103v1 Announce Type: cross Abstract: Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions.
arXiv Machine Learning
Sep 2
Controllable Image Captioning with Prompt-Conditioned Scene Rewards
arXiv:2609.00709v1 Announce Type: cross Abstract: Large Vision-Language Models produce fluent image descriptions but offer limited semantic control: users cannot reliably specify whether captions sho...
arXiv Computer Vision
Sep 2
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
arXiv:2609.00591v1 Announce Type: new Abstract: An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level c...
arXiv Computer Vision
Sep 3
MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation
MMTryon is a multi‑modal, multi‑reference virtual try‑on framework that generates high‑quality compositional try‑on results using text instructions and multiple garment images. It addresses three overlooked problems: supporting multiple try‑on items, allowing dressing style specification via text, and eliminating reliance on segmentation models by using a parsing‑free garment encoder and a scalable data generation pipeline. Experiments on high‑resolution benchmarks and in‑the‑wild test sets show MMTryon outperforms state‑of‑the‑art methods qualitatively and quantitatively.