This paper presents a LoRA-free method for stylized image generation tha...
Large language models (LLMs) have demonstrated impressive impact in the ...
The demand for efficient 3D model generation techniques has grown
expone...
We present SEED, an elaborate image tokenizer that empowers Large Langua...
Image super-resolution (SR) with generative adversarial networks (GAN) h...
Despite the ability of existing large-scale text-to-image (T2I) models t...
This paper introduces DreamDiffusion, a novel method for generating
high...
Enhancing AI systems to perform tasks following human instructions can
s...
Creating a vivid video from the event or scenario in our imagination is ...
Exquisite demand exists for customizing the pretrained large text-to-ima...
Public large-scale text-to-image diffusion models, such as Stable Diffus...
Despite the success in large-scale text-to-image generation and
text-con...
The incredible generative ability of large-scale text-to-image (T2I) mod...
Omnidirectional images (ODIs) have obtained lots of research interest fo...
Recent CLIP-guided 3D optimization methods, e.g., DreamFields and
PureCL...
To reproduce the success of text-to-image (T2I) generation, recent works...
Reference-based Super-Resolution (Ref-SR) has recently emerged as a prom...
The recurrent structure is a prevalent framework for the task of video
s...
The ability to understand and generate similes is an imperative step to
...
Vector-Quantized (VQ-based) generative models usually consist of two bas...
We show that pre-trained Generative Adversarial Networks (GANs) such as
...
Blind face restoration usually encounters with diverse scale face inputs...
The alignment of adjacent frames is considered an essential operation in...
Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding
...
This paper studies the problem of real-world video super-resolution (VSR...
This paper reviews the challenge on constrained high dynamic range (HDR)...
Although generative facial prior and geometric prior have recently
demon...
This paper explores training efficient VGG-style super-resolution (SR)
n...
Despite that convolution neural networks (CNN) have recently demonstrate...
Interactive image restoration aims to restore images by adjusting severa...
Transformer-based methods have shown impressive performance in low-level...
Video colorization is a challenging and highly ill-posed problem. Althou...
Colorization has attracted increasing interest in recent years. Classic
...
Recent blind super-resolution (SR) methods typically consist of two bran...
Though many attempts have been made in blind super-resolution to restore...
Reference-based Super-Resolution (Ref-SR) has recently emerged as a prom...
Blind face restoration usually relies on facial priors, such as facial
g...
SinGAN shows impressive capability in learning internal patch distributi...
We show that pre-trained Generative Adversarial Networks (GANs), e.g.,
S...
Video restoration tasks, including super-resolution, deblurring, etc, ar...
Very deep Convolutional Neural Networks (CNNs) have greatly improved the...
Deep convolutional neural network has demonstrated its capability of lea...
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal...
Despite that convolutional neural networks (CNN) have recently demonstra...