Research map / Image generation / Autoregressive and latent generation
StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning
Giuseppe Vecchio
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add semi-supervised adversarial distillation from SDXL textures (ablation) | StableMaterials · Generation diversity (qualitative, Fig. 8) | diversity / out-of-domain quality | Improved |
| add diffusion refiner stage (SDEdit) after base generation (ablation) | StableMaterials · High-resolution generation (qualitative, Fig. 9a) | sharpness / quality | Improved |
| use two-stage base+refine instead of patched diffusion only (ablation) | StableMaterials · High-resolution generation (qualitative, Fig. 9b) | consistency across patches | Improved |
| replace multi-encoder VAE with single-encoder VAE (271M to 101M params) (ablation) | StableMaterials VAE · VAE reconstruction (5 maps) | RMSE: Albedo 0.030 -> 0.028, Normal 0.035 -> 0.037, Metallic 0.016 -> 0.015 | No clear effect |
| distill LCM with 4 steps and refine for high-res | StableMaterials · Generation time 2048x2048 | time (s): 20.6s -> 4.9s | Improved |
| StableMaterials vs Substance 3D Sampler on perceptual quality | StableMaterials · Text-conditioned generation (80 samples) | CLIP-IQA: 0.71 (Sampler) vs 0.70 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MatFuse — MatFuse: Controllable Material Generation with Diffusion Models (CVPR 2024) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.88)
- Material Anything: Generating Materials for Any 3D Object via Diffusion (CVPR 2025 · similarity 0.87)
- MatFuse: Controllable Material Generation with Diffusion Models (CVPR 2024 · similarity 0.87)
- Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR 2024 · similarity 0.86)
- Scalable Diffusion for Materials Generation (ICLR 2024 · similarity 0.86)
- VLMaterial: Procedural Material Generation with Large Vision-Language Models (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
