Related papers: Beyond the Last Layer: Multi-Layer Representation …
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…
Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work…
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression…
Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and…
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…
In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. In this work, we analyze the role of autoencoders in LDMs and…
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining. Existing methods are mainly targeted at designing complicated modules to implicitly…
In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the…
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…
One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during training, tend to lose…
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we…
Visual complexity prediction is a fundamental problem in computer vision with applications in image compression, retrieval, and classification. Understanding what makes humans perceive an image as complex is also a long-standing question in…
Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…
Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space…
LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focus on sparse voxel representation, overlooking the…
Federated learning is a machine learning paradigm that enables decentralized clients to collaboratively learn a shared model while keeping all the training data local. While considerable research has focused on federated image generation,…
Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…
Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit from strong generative priors, most methods still condition only on low-quality inputs,…
A common pipeline in functional data analysis is to first convert the discretely observed data to smooth functions, and then represent the functions by a finite-dimensional vector of coefficients summarizing the information. Existing…
Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore an effective audio-visual fusion strategy for audiovisual…