# Metappearance: Meta-Learning for Visual Appearance Reproduction

arXiv: https://arxiv.org/abs/2204.08993 · HTML: https://mlsanity.com/paper/2204.08993/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2022.

## Built on by (most cited first, 9 of 9)

- [MatFusion: A Generative Diffusion Model for SVBRDF Capture](https://mlsanity.com/paper/2406.06539/) (2024)
- [Neural Semantic Surface Maps](https://mlsanity.com/paper/2309.04836/) (2023)
- [Plateau-reduced Differentiable Path Tracing](https://mlsanity.com/paper/2211.17263/) (2022)
- [Learning to Learn and Sample BRDFs](https://mlsanity.com/paper/2210.03510/) (2022)
- [SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields](https://mlsanity.com/paper/2409.04482/) (2024)
- [Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics](https://mlsanity.com/paper/2308.05739/) (2023)
- [AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation](https://mlsanity.com/paper/2305.19245/) (2023)
- [Neural Bounding](https://mlsanity.com/paper/2310.06822/) (2023)
- [SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation](https://mlsanity.com/paper/2508.17316/) (2025)

## Abstract (arXiv)

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, 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.