Disentangled representation learning
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …
and disentangling the underlying factors hidden in the observable data in representation …
General image-to-image translation with one-shot image guidance
Large-scale text-to-image models pre-trained on massive text-image pairs show excellent
performance in image synthesis recently. However, image can provide more intuitive visual …
performance in image synthesis recently. However, image can provide more intuitive visual …
InstaFormer: Instance-aware image-to-image translation with transformer
We present a novel Transformer-based network architecture for instance-aware image-to-
image translation, dubbed InstaFormer, to effectively integrate global-and instance-level …
image translation, dubbed InstaFormer, to effectively integrate global-and instance-level …
A comprehensive survey on semantic facial attribute editing using generative adversarial networks
A Nickabadi, MS Fard, NM Farid… - ar**s that can map images
from one domain to another domain while preserving the content of the input image …
from one domain to another domain while preserving the content of the input image …
3D-aware multi-class image-to-image translation with NeRFs
Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural
Radiance Fields (NeRF) have achieved impressive results. However no prior works …
Radiance Fields (NeRF) have achieved impressive results. However no prior works …
Closed-Loop Unsupervised Representation Disentanglement with -VAE Distillation and Diffusion Probabilistic Feedback
Abstract Representation disentanglement may help AI fundamentally understand the real
world and thus benefit both discrimination and generation tasks. It currently has at least …
world and thus benefit both discrimination and generation tasks. It currently has at least …
Lanit: Language-driven image-to-image translation for unlabeled data
Existing techniques for image-to-image translation commonly have suffered from two critical
problems: heavy reliance on per-sample domain annotation and/or inability to handle …
problems: heavy reliance on per-sample domain annotation and/or inability to handle …