mlsanityData to 14 Oct 2026

Learning to Learn and Sample BRDFs

arXiv 2210.03510 ↗First posted 7 Oct 2022cs.GR cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose a method to accelerate the joint process of physically acquiring and learning neural Bi-directional Reflectance Distribution Function (BRDF) models. While BRDF learning alone can be accelerated by meta-learning, acquisition remains slow as it relies on a mechanical process. We show that meta-learning can be extended to optimize the physical sampling pattern, too. After our method has been meta-trained for a set of fully-sampled BRDFs, it is able to quickly train on new BRDFs with up to five orders of magnitude fewer physical acquisition samples at similar quality. Our approach also extends to other linear and non-linear BRDF models, which we show in an extensive evaluation.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 29 of its 65 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

29 of 65 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2015Variational Inference with Normalizing Flowscited by 2,170
  5. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  6. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  7. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
  8. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  9. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  10. 2013Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithmcited by 133
  11. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  12. 2014Stochastic Optimization with Importance Samplingcited by 91
17 more
  1. 2021Real-time Neural Radiance Caching for Path Tracingcited by 91
  2. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  3. 2020learn2learn: A Library for Meta-Learning Researchcited by 69
  4. 2021Generative Modelling of BRDF Textures from Flash Imagescited by 35
  5. 2020MaterialGAN: Reflectance Capture using a Generative SVBRDF Modelcited by 33
  6. 2021Fast Training of Neural Lumigraph Representations using Meta Learningcited by 29
  7. 2021Neural BRDF Representation and Importance Samplingcited by 28
  8. 2020Guided Fine-Tuning for Large-Scale Material Transfercited by 27
  9. 2020Seeing the World in a Bag of Chipscited by 25
  10. 2017Safe Adaptive Importance Samplingcited by 19
  11. 2017Material Editing Using a Physically Based Rendering Networkcited by 17
  12. 2015Deep Reflectance Mapscited by 13
  13. 2022Active Exploration for Neural Global Illumination of Variable Scenescited by 11
  14. 2015Online Learning to Samplecited by 10
  15. 2022Metappearance: Meta-Learning for Visual Appearance Reproductioncited by 9
  16. 2018Deep Appearance Mapscited by 7
  17. 2021Neural BRDFs: Representation and Operationscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 0; 2026: 2.

9 papers.

  1. 2023Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environmentscited by 19
  2. 2023Neural Semantic Surface Mapscited by 13
  3. 2024NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFscited by 11
  4. 2022Plateau-reduced Differentiable Path Tracingcited by 10
  5. 2024Physically Based Neural Bidirectional Reflectance Distribution Functioncited by 1
  6. 2023Neural Boundingcited by 0
  7. 2024Deep image-based Adaptive BRDF Measurecited by 0
  8. 2026Rendering-Aware Sparse Sampling for BRDF Acquisitioncited by 0
  9. 2026Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectancecited by 0