# MaRI: Material Retrieval Integration across Domains

arXiv: https://arxiv.org/abs/2503.08111 · HTML: https://mlsanity.com/paper/2503.08111/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://mlsanity.com/paper/2303.14184/) (2023)
- [Infinite Photorealistic Worlds using Procedural Generation](https://mlsanity.com/paper/2306.09310/) (2023)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [Deep Polarization Imaging for 3D shape and SVBRDF Acquisition](https://mlsanity.com/paper/2105.02875/) (2021)
- [ControlMat: A Controlled Generative Approach to Material Capture](https://mlsanity.com/paper/2309.01700/) (2023)
- [MatFuse: Controllable Material Generation with Diffusion Models](https://mlsanity.com/paper/2308.11408/) (2023)
- [Material Palette: Extraction of Materials from a Single Image](https://mlsanity.com/paper/2311.17060/) (2023)
- [TileGen: Tileable, Controllable Material Generation and Capture](https://mlsanity.com/paper/2206.05649/) (2022)
- [MaPa: Text-driven Photorealistic Material Painting for 3D Shapes](https://mlsanity.com/paper/2404.17569/) (2024)
- [Materialistic: Selecting Similar Materials in Images](https://mlsanity.com/paper/2305.13291/) (2023)
- [ZeST: Zero-Shot Material Transfer from a Single Image](https://mlsanity.com/paper/2404.06425/) (2024)
- [PhotoShape: Photorealistic Materials for Large-Scale Shape Collections](https://mlsanity.com/paper/1809.09761/) (2018)
- [Generating Procedural Materials from Text or Image Prompts](https://mlsanity.com/paper/2304.13172/) (2023)
- [A Similarity Measure for Material Appearance](https://mlsanity.com/paper/1905.01562/) (2019)
- [PhotoMat: A Material Generator Learned from Single Flash Photos](https://mlsanity.com/paper/2305.12296/) (2023)
- [Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials](https://mlsanity.com/paper/2404.16829/) (2024)
- [MatFormer: A Generative Model for Procedural Materials](https://mlsanity.com/paper/2207.01044/) (2022)

## Built on by (most cited first, 2 of 2)

- [Gated Multimodal Graph Learning for Personalized Recommendation](https://mlsanity.com/paper/2506.00107/) (2025)
- [FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow](https://mlsanity.com/paper/2603.19598/) (2026)

## Abstract (arXiv)

Accurate material retrieval is critical for creating realistic 3D assets. Existing methods rely on datasets that capture shape-invariant and lighting-varied representations of materials, which are scarce and face challenges due to limited diversity and inadequate real-world generalization. Most current approaches adopt traditional image search techniques. They fall short in capturing the unique properties of material spaces, leading to suboptimal performance in retrieval tasks. Addressing these challenges, we introduce MaRI, a framework designed to bridge the feature space gap between synthetic and real-world materials. MaRI constructs a shared embedding space that harmonizes visual and material attributes through a contrastive learning strategy by jointly training an image and a material encoder, bringing similar materials and images closer while separating dissimilar pairs within the feature space. To support this, we construct a comprehensive dataset comprising high-quality synthetic materials rendered with controlled shape variations and diverse lighting conditions, along with real-world materials processed and standardized using material transfer techniques. Extensive experiments demonstrate the superior performance, accuracy, and generalization capabilities of MaRI across diverse and complex material retrieval tasks, outperforming existing methods.