RATR: Training-Free Material Rebinding via Role Assignment and Temporal Routing
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/TangJieH/RATR
License: http://creativecommons.org/licenses/by/4.0/
The gist: Material rebinding aims to transfer the material appearance from a reference image while preserving the target object's geometry and identity.
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.
Sources
- MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
- Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
- CoatFusion: Controllable Material Coating in Images
- InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
- Qwen-Image Technical Report
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs