Related papers: Fully Convolutional Network with Multi-Step Reinfo…

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.…

Supervised learning, more specifically Convolutional Neural Networks (CNN), has surpassed human ability in some visual recognition tasks such as detection of traffic signs, faces and handwritten numbers. On the other hand, even…

Reinforcement Learning (RL) has presented an impressive performance in video games through raw pixel imaging and continuous control tasks. However, RL performs poorly with high-dimensional observations such as raw pixel images. It is…

Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the…

Image Inpainting is one of the very popular tasks in the field of image processing with broad applications in computer vision. In various practical applications, images are often deteriorated by noise due to the presence of corrupted, lost,…

Reinforcement Learning (RL) is a well-established framework for sequential decision-making in complex environments. However, state-of-the-art Deep RL (DRL) algorithms typically require large training datasets and often struggle to…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior…

Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-based image restoration models is suboptimal, as the objective…

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…

We present highly efficient algorithms for performing forward and backward propagation of Convolutional Neural Network (CNN) for pixelwise classification on images. For pixelwise classification tasks, such as image segmentation and object…

In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In…

In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object recognition. In most realistic computer vision applications,…

Very deep Convolutional Neural Networks (CNNs) have greatly improved the performance on various image restoration tasks. However, this comes at a price of increasing computational burden, hence limiting their practical usages. We observe…

Deep Reinforcement Learning (DRL) has produced great achievements since it was proposed, including the possibility of processing raw vision input data. However, training an agent to perform tasks based on image feedback remains a challenge.…

While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the task of text-guided image editing remains a challenge. Even edit requests that consist of only a few…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

We propose a new approach for the image super-resolution (SR) task that progressively restores a high-resolution (HR) image from an input low-resolution (LR) image on the basis of a neural ordinary differential equation. In particular, we…