This adversarial loss guarantees the map is diverse -- a very wide range of anime can be produced from a single content code.
Ranked #1 on Image-to-Image Translation on selfie2anime
Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.
We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders.
Ranked #1 on Semantic Segmentation on Cityscapes val
In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.
Ranked #1 on Face Swapping on FaceForensics++ (ID retrieval metric)
We propose Styleformer, which is a style-based generator for GAN architecture, but a convolution-free transformer-based generator.
Ranked #1 on Image Generation on CelebA 64x64
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice.
Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.
Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data.
We devise a hybrid deep learning approach to solving tabular data problems.
We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent.