Recovering Geometric Information with Learned Texture Perturbations
| dc.contributor.author | Wu, Jane | en_US |
| dc.contributor.author | Jin, Yongxu | en_US |
| dc.contributor.author | Geng, Zhenglin | en_US |
| dc.contributor.author | Zhou, Hui | en_US |
| dc.contributor.author | Fedkiw, Ronald | en_US |
| dc.contributor.editor | Narain, Rahul and Neff, Michael and Zordan, Victor | en_US |
| dc.date.accessioned | 2022-02-07T13:32:35Z | |
| dc.date.available | 2022-02-07T13:32:35Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Regularization is used to avoid overfitting when training a neural network; unfortunately, this reduces the attainable level of detail hindering the ability to capture high-frequency information present in the training data. Even though various approaches may be used to re-introduce high-frequency detail, it typically does not match the training data and is often not time coherent. In the case of network inferred cloth, these sentiments manifest themselves via either a lack of detailed wrinkles or unnaturally appearing and/or time incoherent surrogate wrinkles. Thus, we propose a general strategy whereby high-frequency information is procedurally embedded into low-frequency data so that when the latter is smeared out by the network the former still retains its high-frequency detail. We illustrate this approach by learning texture coordinates which when smeared do not in turn smear out the high-frequency detail in the texture itself but merely smoothly distort it. Notably, we prescribe perturbed texture coordinates that are subsequently used to correct the over-smoothed appearance of inferred cloth, and correcting the appearance from multiple camera views naturally recovers lost geometric information. | en_US |
| dc.description.number | 3 | |
| dc.description.sectionheaders | papers | |
| dc.description.seriesinformation | Proceedings of the ACM on Computer Graphics and Interactive Techniques | |
| dc.description.volume | 4 | |
| dc.identifier.doi | 10.1145/3480137 | |
| dc.identifier.issn | 2577-6193 | |
| dc.identifier.uri | https://doi.org/10.1145/3480137 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1145/3480137 | |
| dc.publisher | ACM | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Animation | |
| dc.subject | Neural networks | |
| dc.subject | Computer vision representations | |
| dc.subject | cloth | |
| dc.subject | folds | |
| dc.subject | wrinkles | |
| dc.subject | neural networks | |
| dc.title | Recovering Geometric Information with Learned Texture Perturbations | en_US |