MARBLE: Material Recomposition and Blending in CLIP-Space
Ta Ying Cheng, Prafull Sharma, Mark Boss, Varun Jampani
Abstract
Figure 1 . Overview. We present MARBLE, a method for performing various material editing in images such as material blending (top row) and parametric control of material properties (bottom row) leveraging CLIP-space and pre-trained generative models. Given two material exemplar images, we can achieve a controllable blend of materials on the object by blending the material representation in CLIP-space. For parametric material attribute control, we learn a shallow network using synthetic data to predict the direction in CLIP-space for changing specific material properties such as metallic.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- Kontinuous Kontext: Continuous Strength Control for Instruction-based Image EditingRishubh Parihar, Or Patashnik, Daniil Ostashev, Venkatesh Babu Radhakrishnan et al.CVPR 2026 · 15 citations
- Continuous Control of Editing Models via Adaptive-Origin GuidanceAlon Wolf, Chen Katzir, Kfir Aberman, Or PatashnikSIGGRAPH 2026
Builds on32
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion ModelsAlexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam et al.ICML 2022 · 4,691 citations
Related papers
- Alchemist: Parametric Control of Material Properties with Diffusion ModelsPrafull Sharma, Varun Jampani, Yuanzhen Li, Xuhui Jia et al.CVPR 2024 · 16 citations
- TexSliders: Diffusion-Based Texture Editing in CLIP SpaceJulia Guerrero-Viu, Milos Hasan, Arthur Roullier, Midhun Harikumar et al.SIGGRAPH 2024 · 18 citations
- Text2Mesh: Text-Driven Neural Stylization for MeshesOscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim et al.CVPR 2022
- CLIPTexture: Text-Driven Texture SynthesisYiren SongACM MM 2022 · 7 citations
- Materialistic: Selecting Similar Materials in ImagesPrafull Sharma, Julien Philip, Michaël Gharbi, Bill Freeman et al.SIGGRAPH 2023 · 23 citations
