Related papers: NARAIM: Native Aspect Ratio Autoregressive Image M…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…
Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products. Same as MNIST, the handwritten digit images, SIIs are gray or binary and containing shapes that are surrounded by large areas…
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images. Most of these algorithms assume the degradation is fixed and known a priori. However, in…
Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…
View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high…
Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a…
We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…
For all the ways convolutional neural nets have revolutionized computer vision in recent years, one important aspect has received surprisingly little attention: the effect of image size on the accuracy of tasks being trained for. Typically,…
Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…
Image colorization, the task of adding colors to grayscale images, has been the focus of significant research efforts in computer vision in recent years for its various application areas such as color restoration and automatic animation…
Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to real-time computational resources. This challenge impedes…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
We present Large Inverse Rendering Model (LIRM), a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second. Our model builds upon the recent…
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation. They leverage the probability product rule and a…
The field of neural image compression has witnessed exciting progress as recently proposed architectures already surpass the established transform coding based approaches. While, so far, research has mainly focused on architecture and model…
Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…
Inverse rendering aims to estimate physical attributes of a scene, e.g., reflectance, geometry, and lighting, from image(s). Inverse rendering has been studied primarily for single objects or with methods that solve for only one of the…
Human vision involves parsing and representing objects and scenes using structured representations based on part-whole hierarchies. Computer vision and machine learning researchers have recently sought to emulate this capability using…
Many interesting tasks in image restoration can be cast as linear inverse problems. A recent family of approaches for solving these problems uses stochastic algorithms that sample from the posterior distribution of natural images given the…