Fischer, Michael;
Ritschel, Tobias;
(2022)
Metappearance: Meta-Learning for Visual Appearance Reproduction.
In:
ACM Transactions on Graphics.
Association for Computing Machinery (ACM)
Preview |
Text
2204.08993v2.pdf - Accepted Version Download (32MB) | Preview |
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Metappearance: Meta-Learning for Visual Appearance Reproduction |
| Event: | SIGGRAPH Asia Conference |
| Location: | SOUTH KOREA, Daegu |
| Dates: | 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3550454.3555458 |
| Publisher version: | http://doi.org/10.1145/3550454.3555458 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | BRDFs, Computer Science, Computer Science, Software Engineering, Deep Learning, Light Transport, Meta-Learning, Science & Technology, svBRDFs, Technology, Visual Appearance |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10192086 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
