Affiliation:
1. University College London, United Kingdom
Abstract
There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot approaches, these offer fast inference, but often fall short in quality. The second approach does not train models that generalize across tasks, but rather over-fit a single instance of a problem, e.g., a flash image of a material. These methods offer high quality, but take long to train. We suggest to combine both techniques end-to-end using meta-learning: We over-fit onto a single problem instance in an inner loop, while also learning how to do so efficiently in an outer-loop across many exemplars. To this end, we derive the required formalism that allows applying meta-learning to a wide range of visual appearance reproduction problems: textures, Bidirectional Reflectance Distribution Functions (BRDFs), spatially-varying BRDFs (svBRDFs), illumination or the entire light transport of a scene. The effects of meta-learning parameters on several different aspects of visual appearance are analyzed in our framework, and specific guidance for different tasks is provided. Metappearance enables visual quality that is similar to over-fit approaches in only a fraction of their runtime while keeping the adaptivity of general models.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Reference60 articles.
1. Learned Primal-Dual Reconstruction
2. Reflectance modeling by neural texture synthesis
3. Maruan Al-Shedivat , Liam Li , Eric Xing , and Ameet Talwalkar . 2021 . On data efficiency of meta-learning . In International Conference on Artificial Intelligence and Statistics. PMLR, 1369--1377 . Maruan Al-Shedivat, Liam Li, Eric Xing, and Ameet Talwalkar. 2021. On data efficiency of meta-learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 1369--1377.
4. Antreas Antoniou , Harrison Edwards , and Amos Storkey . 2018. How to train your MAML. arXiv:1810.09502 ( 2018 ). Antreas Antoniou, Harrison Edwards, and Amos Storkey. 2018. How to train your MAML. arXiv:1810.09502 (2018).
5. Offline Deep Importance Sampling for Monte Carlo Path Tracing
Cited by
10 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. ZeroGrads: Learning Local Surrogates for Non-Differentiable Graphics;ACM Transactions on Graphics;2024-07-19
2. Neural Bounding;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13
3. MatUp: Repurposing Image Upsamplers for SVBRDFs;Computer Graphics Forum;2024-07
4. Single‐Image SVBRDF Estimation with Learned Gradient Descent;Computer Graphics Forum;2024-04-23
5. Neural Semantic Surface Maps;Computer Graphics Forum;2024-04-17