Related papers: Towards Real World HDRTV Reconstruction: A Data Sy…

Synthetic data generated by text-to-speech (TTS) systems can be used to improve automatic speech recognition (ASR) systems in low-resource or domain mismatch tasks. It has been shown that TTS-generated outputs still do not have the same…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…

Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack of ground truth references for training. Recent self-supervised learning strategies offer…

End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occur in unseen domains (e.g., when moving from synthetic to…

Spatially resolved transcriptomics (SRT) has evolved rapidly through various technologies, enabling scientists to investigate both morphological contexts and gene expression profiling at single-cell resolution in parallel. SRT data are…

We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to…

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction…

Researches in novel viewpoint synthesis majorly focus on interpolation from multi-view input images. In this paper, we focus on a more challenging and ill-posed problem that is to synthesize novel viewpoints from one single input image. To…

We present a new pipeline for acquiring a textured mesh in the wild with a single smartphone which offers access to images, depth maps, and valid poses. Our method first introduces an RGBD-aided structure from motion, which can yield…

We present a self-supervised speech restoration method without paired speech corpora. Because the previous general speech restoration method uses artificial paired data created by applying various distortions to high-quality speech corpora,…

Deep learning methods have been successfully used in various computer vision tasks. Inspired by that success, deep learning has been explored in magnetic resonance imaging (MRI) reconstruction. In particular, integrating deep learning and…

Underwater object detection suffers from low detection performance because the distance and wavelength dependent imaging process yield evident image quality degradations such as haze-like effects, low visibility, and color distortions.…

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The…

Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the…

Capturing the shape and spatially-varying appearance (SVBRDF) of an object from images is a challenging task that has applications in both computer vision and graphics. Traditional optimization-based approaches often need a large number of…

Advanced driver assistance systems (ADAS) relying on multiple cameras are increasingly prevalent in vehicle technology. Yet, conventional imaging sensors struggle to capture clear images in conditions with intense illumination contrast,…

Use of synthetic data has provided a potential solution for addressing unavailable or insufficient training samples in deep learning-based magnetic resonance imaging (MRI). However, the challenge brought by domain gap between synthetic and…

Majority of state-of-the-art monocular depth estimation methods are supervised learning approaches. The success of such approaches heavily depends on the high-quality depth labels which are expensive to obtain. Some recent methods try to…

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can…