Deep generative models, which target reproducing the data distribution to produce novel
images, have made unprecedented advancements in recent years. However, one critical …

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint
between the query network and the larger gallery network. However these one-to-one …

In this paper we delve into a novel aspect of learning novel diffusion conditions with datasets
an order of magnitude smaller. The rationale behind our approach is the elimination of …

Low-resource settings are well-established in natural lan-guage processing where many
languages lack sufficient data for deep learning at scale. However low-resource problems …

In machine learning, generative modeling aims to learn to generate new data statistically
similar to the training data distribution. In this paper, we survey learning generative models …

GAN inversion is indispensable for applying the powerful editability of GAN to real images.
However, existing methods invert video frames individually often leading to undesired …

Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …

We propose a voxel-based optimization framework ReVoRF for few-shot radiance fields that
strategically addresses the unreliability in pseudo novel view synthesis. Our method pivots …

Few-shot image generation as an important yet challenging visual task still suffers from the
trade-off between generation quality and diversity. According to the principle of feature …

SAR images possess unique attributes that present challenges for both human observers
and vision AI models to interpret, owing to their electromagnetic characteristics. The …