MARBLE: Material Recomposition and Blending in CLIP-Space

TL;DR

MARBLE is a novel technique that enables fine-grained material editing in images by leveraging CLIP-space embeddings, allowing for blending, recomposing, and attribute control of materials with high flexibility and efficiency.

Contribution

We introduce MARBLE, a method that finds material embeddings in CLIP-space for advanced material editing, including blending, recomposing, and attribute manipulation, with a focus on fine-grained control.

Findings

Effective material blending and recomposing demonstrated.

Parametric control over material attributes achieved.

Multiple edits performed in a single forward pass.

Abstract

Editing materials of objects in images based on exemplar images is an active area of research in computer vision and graphics. We propose MARBLE, a method for performing material blending and recomposing fine-grained material properties by finding material embeddings in CLIP-space and using that to control pre-trained text-to-image models. We improve exemplar-based material editing by finding a block in the denoising UNet responsible for material attribution. Given two material exemplar-images, we find directions in the CLIP-space for blending the materials. Further, we can achieve parametric control over fine-grained material attributes such as roughness, metallic, transparency, and glow using a shallow network to predict the direction for the desired material attribute change. We perform qualitative and quantitative analysis to demonstrate the efficacy of our proposed method. We also present the ability of our method to perform multiple edits in a single forward pass and applicability to painting. Project Page: https://marblecontrol.github.io/