TryOn-Refiner: Conditional Rectified-Flow-Based Tryon Refiner for More Accurate Detail Reconstruction

Wen Qian

doi:10.1109/iccv51701.2025.01454

ICCV2025顶会

TryOn-Refiner: Conditional Rectified-Flow-Based Tryon Refiner for More Accurate Detail Reconstruction

Wen Qian

DOI 出版方

2025年份

摘要

Refinements of patterns (b) Refinements of texts (c) Refinements of faces Figure 1. The refined results of our TryOn-Refiner. The left column shows the course try-on results generated by existing SOTA try-on methods. TryOn-Refiner can refine various types of artifacts including patterns, texts and faces, etc.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。

核心论断
横向对比
局限

你的问题

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始，无需绑卡

它引用的顶会 Paper33

Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 被引用 11,724 次
Denoising Diffusion Restoration ModelsBahjat Kawar, Michael Elad, Stefano Ermon, Jiaming SongNeurIPS 2022 · 被引用 1,439 次
Score-Based Generative Modeling through Stochastic Differential EquationsYang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar 等ICLR 2021 · 被引用 1,270 次

摘要

问问这篇 Paper

智能体会读完全文。

它引用的顶会 Paper33

相关 Paper