Pre-trained large text-to-image models synthesize impressive images with...
We investigate the potential of learning visual representations using
sy...
We study domain-adaptive image synthesis, the problem of teaching pretra...
It is important in computational imaging to understand the uncertainty o...
We propose Stratified Image Transformer(StraIT), a pure
non-autoregressi...
Generative modeling and representation learning are two key tasks in com...
We introduce CAN, a simple, efficient and scalable method for self-super...
Text-conditioned image editing has recently attracted considerable inter...
Transferring knowledge from an image synthesis model trained on a large
...
Non-autoregressive generative transformers recently demonstrated impress...
Generative transformers have experienced rapid popularity growth in the
...
Creating visual layouts is an important step in graphic design. Automati...
Aggressive data augmentation is a key component of the strong generaliza...
We introduce Palette, a simple and general framework for image-to-image
...
Single image 3D photography enables viewers to view a still image from n...
Recently, Vision Transformers (ViTs) have shown competitive performance ...
Remarkable progress has been made in 3D reconstruction of rigid structur...
Synthetic datasets play a critical role in pre-training CNN models for
o...
Digital watermarking is widely used for copyright protection. Traditiona...
Video watermarking embeds a message into a cover video in an imperceptib...
Watermarking is the process of embedding information into an image that ...