Learning Compositional Shape Priors for Few-Shot 3D Reconstruction
| Autor: | Michalkiewicz, Mateusz, Tsogkas, Stavros, Parisot, Sarah, Baktashmotlagh, Mahsa, Eriksson, Anders, Belilovsky, Eugene |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief, showing that, on standard benchmarks, complex encoder-decoder architectures perform similarly to nearest-neighbor baselines or simple linear decoder models that exploit large amounts of per-category data. However, building large collections of 3D shapes for supervised training is a laborious process; a more realistic and less constraining task is inferring 3D shapes for categories with few available training examples, calling for a model that can successfully generalize to novel object classes. In this work we experimentally demonstrate that naive baselines fail in this few-shot learning setting, in which the network must learn informative shape priors for inference of new categories. We propose three ways to learn a class-specific global shape prior, directly from data. Using these techniques, we are able to capture multi-scale information about the 3D shape, and account for intra-class variability by virtue of an implicit compositional structure. Experiments on the popular ShapeNet dataset show that our method outperforms a zero-shot baseline by over 40%, and the current state-of-the-art by over 10%, in terms of relative performance, in the few-shot setting. Comment: 13 pages, 12 figures. arXiv admin note: substantial text overlap with arXiv:2004.06302 |
| Databáze: | arXiv |
| Externí odkaz: |
|