Browse Proceedings

Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distributions by training a model on a variety of datasets, with results ...

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via ...

Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expensive in practice to annotate all labels in every training image. ...

Semantic segmentation is a key computer vision task that has been actively researched for decades. In recent years, supervised methods have reached unprecedented accuracy; however, obtaining pixel-level annotation is very time-consuming and ...

Representation disentanglement is an important goal of the representation learning that benefits various of downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However, ...

Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR ...

Out-of-distribution detection seeks to identify novelties, samples that deviate from the norm. The task has been found to be quite challenging, particularly in the case where the normal data distribution consist of multiple semantic classes (e.g. ...

Due to the high transferability of features extracted from early layers (called local features), aligning marginal distributions of local features has achieved compelling results in unsupervised domain adaptive object detection. However, such ...

Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may contain out-of-class ...

One of the primary challenges in Semi-supervised Domain Adaptation (SSDA) is the skewed ratio between the number of labeled source and target samples, causing the model to be biased towards the source domain. Recent works in SSDA show that ...

Deep learning-based image super-resolution (SR) has shown its strong capability in recovering high-resolution image details from low-resolution inputs. With the ubiquitous use of AI-accelerators on mobile devices (e.g., smartphones), increasing ...

The goal of semantic image editing is to modify an image based on an input semantic label map, to carry out the necessary image manipulation. Existing approaches typically lack control over the style of the editing, resulting in insufficient ...

StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare it to ...$\mathcal{}\mathcal{}$

The key to shadow removal is recovering the contents of the shadow regions with the guidance of the non-shadow regions. Due to the inadequate long-range modeling, the CNN-based approaches cannot thoroughly investigate the information from the non-...

Generative image models have been extensively studied in recent years. In the unconditional setting, they model the marginal distribution from unlabelled images. To allow for more control, image synthesis can be conditioned on semantic ...

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually ...

Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Without the need for sketch and photo pairs, our framework directly ...

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various ...

With an unprecedented increase in the number of agents and systems that aim to navigate the real world using visual cues and the rising impetus for 3D Vision Models, the importance of depth estimation is hard to understate. While supervised ...

This paper aims at exploring how to synthesize close-to-real blurs that existing video deblurring models trained on them can generalize well to real-world blurry videos. In recent years, deep learning-based approaches have achieved promising ...

Vision based applications routinely involve restoration as a preprocessing step, making it impossible to have separate architectures for different types of weather restoration. But, most of the existing methods focus on weather specific ...${}^{\mathit{}}$

Despite achieving remarkable progress in recent years, single-image super-resolution methods are developed with several limitations. Specifically, they are trained on fixed content domains with certain degradations (whether synthetic or real). The ...

High dynamic range (HDR) imaging is still a challenging task in modern digital photography. Recent research proposes solutions that provide high-quality acquisition but at the cost of a very large number of operations and a slow inference time ...$$

Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and Generative Adversarial Networks (GANs) have proven to be effective ...

Light field (LF) angular super-resolution (SR) aims at reconstructing a densely sampled LF from a sparsely sampled one. To achieve accurate angular SR, it is important but challenging to incorporate the complementary information among input views, ...

Bokeh effect highlights an object (or any part of the image) while blurring the rest of the image, and creates a visually pleasant artistic effect. Due to the sensor-based limitations on mobile devices, machine learning (ML) based bokeh rendering ...