Toward Spatially Unbiased Generative Models
Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen locations and scales. We argue that the generators rely on their implicit positional enc...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Recent image generation models show remarkable generation performance.
However, they mirror strong location preference in datasets, which we call
spatial bias. Therefore, generators render poor samples at unseen locations and
scales. We argue that the generators rely on their implicit positional encoding
to render spatial content. From our observations, the generator's implicit
positional encoding is translation-variant, making the generator spatially
biased. To address this issue, we propose injecting explicit positional
encoding at each scale of the generator. By learning the spatially unbiased
generator, we facilitate the robust use of generators in multiple tasks, such
as GAN inversion, multi-scale generation, generation of arbitrary sizes and
aspect ratios. Furthermore, we show that our method can also be applied to
denoising diffusion probabilistic models. |
---|---|
DOI: | 10.48550/arxiv.2108.01285 |