cs.CVOct 31, 2026

RATR: Training-Free Material Rebinding via Role Assignment and Temporal Routing

Authors: Jiehui Tang, Yunlong Yu, Zhao Wang, Jungong Han

Organizations: College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China . · Ningbo Innovation Center, Zhejiang University, Ningbo, China . · Department of Automation, Tsinghua University, Beijing, China .

Abstract

Material rebinding aims to transfer the material appearance from a reference image while preserving the target object's geometry and identity. Existing methods typically struggle to balance material fidelity with structural preservation due to the coupled influence of structural and appearance cues in their visual conditions. We identify role entanglement in the target and reference conditions as a contributing factor the target condition carries both geometry and its original appearance while the reference condition contains material cues alongside object-specific structure. To address this issue, we propose RATR, a training-free material rebinding method built on a diffusion-based image editor that assigns complementary roles to the two conditions and coordinates their influence during denoising. To make the target condition primarily convey structure, we introduce an albedo-resolved surface release mechanism, which suppresses the target's original surface appearance while retaining geometric cues, yielding a structure-oriented condition for material transfer. On the reference side, the designed material evidence isolation mechanism emphasizes material cues while reducing interference from object-specific structure, yielding a complementary material-oriented condition.

Figures & tables

Explore similar work

CardsList
  1. DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

    May 15, 2026Nisha Huang, Yizhou Lin, Jie Guo +3Diffusion TransformerDiffusion-Based Image Editing

  2. MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes

    Aug 25, 2026Mingzhe Du, Thong Thanh Nguyen, Nguyen Tran Cong Duy +2Image Editing EvaluationImage Generation

  3. MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer

    May 15, 2026Nisha Huang, Henglin Liu, Yizhou Lin +5Diffusion TransformerDiffusion-Based Image Editing