Learning Sparse BRDF Measurement Samples from Image
TLDR
This paper introduces a method to select optimal sparse BRDF measurements for material reconstruction using a learned prior and differentiable rendering.
Key contributions
- Proposes a novel sampler to select optimal sparse BRDF measurements for material reconstruction.
- Combines a set encoder, a fixed hypernetwork BRDF reconstructor, and a differentiable renderer.
- Optimizes measurement locations using BRDF-space and rendered-image losses, separating sample selection from prior fitting.
- Achieves improved low-budget BRDF reconstruction quality with 8-16 measurements on the MERL dataset.
Why it matters
Accurate BRDF acquisition is crucial for realistic rendering but traditionally slow. This method offers a way to significantly reduce measurement costs while maintaining quality, especially for low-budget scenarios. It enables more efficient material scanning for graphics and vision applications.
Original Abstract
Accurate BRDF acquisition is important for realistic rendering, but dense gonioreflectometer measurements are slow and expensive. We study how to select a small number of BRDF measurements that are most useful for reconstructing material appearance under a learned reflectance prior. Our method combines a set encoder for sparse coordinate-value observations, a pretrained hypernetwork-based BRDF reconstructor, and a differentiable renderer. During sampler training, the reconstructor is kept fixed and gradients from BRDF-space and rendered-image losses are used to optimize measurement locations. This separates sample selection from prior fitting and encourages the sampler to choose directions that are informative under the learned material distribution. Experiments on the MERL dataset show that the proposed sampler improves low-budget reconstruction quality at 8 and 16 measurements compared with neural reconstruction baselines, while PCA-based methods remain strong at larger budgets. We further analyze the effect of image-space supervision, co-optimization, and image-only latent fitting for unseen materials.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.