Dress-ED is the first large-scale benchmark unifying virtual try-on, try-off, and text-guided garment editing with 146k verified samples plus a multimodal diffusion baseline.
In: NeurIPS (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
citing papers explorer
-
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
Dress-ED is the first large-scale benchmark unifying virtual try-on, try-off, and text-guided garment editing with 146k verified samples plus a multimodal diffusion baseline.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.