LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
Not on the map. Why?
Abstract (arXiv)
Physically-based rendering (PBR) provides a principled standard for realistic material-lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limited illumination cues, and 2) seamless and view-consistent texture completion. To this end, we propose LumiTex, an end-to-end framework that comprises three key components: (1) a multi-branch generation scheme that disentangles albedo and metallic-roughness under shared illumination priors for robust material understanding, (2) a lighting-aware material attention mechanism that injects illumination context into the decoding process for physically grounded generation of albedo, metallic, and roughness maps, and (3) a geometry-guided inpainting module based on a large view synthesis model that enriches texture coverage and ensures seamless, view-consistent UV completion. Extensive experiments demonstrate that LumiTex achieves state-of-the-art performance in texture quality, surpassing both existing open-source and commercial methods.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 74 of its 81 references that are in the map. First posted on arXiv 24 Nov 2025.
Builds on
74 of 81 references.
References · 74
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
- 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
38 more
- 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
- 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
- 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
- 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
- 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
- 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
- 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
- 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
- 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
- 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
- 2022CLIP-Mesh: Generating textured meshes from text using pretrained image-text modelscited by 281
- 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
- 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
- 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
- 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 159
- 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 122
- 2025Test-Time Training Done Rightcited by 121
- 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
- 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 111
- 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
- 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
- 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
- 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
- 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
- 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
- 2022TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decompositioncited by 83
- 2023Intrinsic Image Diffusion for Indoor Single-view Material Estimationcited by 73
- 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusioncited by 72
- 2024IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illuminationcited by 67
- 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
- 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
- 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
- 2020Two-shot Spatially-varying BRDF and Shape Estimationcited by 59
- 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Modelscited by 55
- 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
- 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 51
50 most cited of 74 All 74 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.