{"ID":2884412,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07011","arxiv_id":"2508.07011","title":"HiMat: DiT-based Ultra-High Resolution SVBRDF Generation","abstract":"Creating ultra-high-resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine-scale surface details required for close-up rendering. However, achieving 4K generation faces two key challenges: (1) the need to synthesize multiple reflectance maps at full resolution, which multiplies the pixel budget and imposes prohibitive memory and computational cost, and (2) the requirement to maintain strong pixel-level alignment across maps at 4K, which is particularly difficult when adapting pretrained models designed for the RGB image domain. We introduce HiMat, a diffusion-based framework tailored for efficient and diverse 4K SVBRDF generation. To address the first challenge, HiMat performs generation in a high-compression latent space via DC-AE, and employs a pretrained diffusion transformer with linear attention to improve per-map efficiency. To address the second challenge, we propose CrossStitch, a lightweight convolutional module that enforces cross-map consistency without incurring the cost of global attention. Our experiments show that HiMat achieves high-fidelity 4K SVBRDF generation with superior efficiency, structural consistency, and diversity compared to prior methods. Beyond materials, our framework also generalizes to related applications such as intrinsic decomposition.","short_abstract":"Creating ultra-high-resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine-scale surface details required for close-up rendering. However, achieving 4K generation faces two key challenges: (1) the need to synthesize mul...","url_abs":"https://arxiv.org/abs/2508.07011","url_pdf":"https://arxiv.org/pdf/2508.07011v4","authors":"[\"Zixiong Wang\",\"Jian Yang\",\"Yiwei Hu\",\"Milos Hasan\",\"Beibei Wang\"]","published":"2025-08-09T15:16:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}