Related papers: Motion-Adapted Three-Dimensional Frequency Selecti…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention…
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the…
We propose FocusTune, a focus-guided sampling technique to improve the performance of visual localization algorithms. FocusTune directs a scene coordinate regression model towards regions critical for 3D point triangulation by exploiting…
As Deep Neural Networks are becoming more popular, much of the attention is being devoted to Computer Vision problems that used to be solved with more traditional approaches. Video frame interpolation is one of such challenges that has seen…
Sharpening is a widely adopted technique to improve video quality, which can effectively emphasize textures and alleviate blurring. However, increasing the sharpening level comes with a higher video bitrate, resulting in degraded Quality of…
In sparse coding, we attempt to extract features of input vectors, assuming that the data is inherently structured as a sparse superposition of basic building blocks. Similarly, neural networks perform a given task by learning features of…
This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\text{F}^3$). We learn this representation by predicting future events from past…
Low-light image enhancement is a classical computer vision problem aiming to recover normal-exposure images from low-light images. However, convolutional neural networks commonly used in this field are good at sampling low-frequency local…
Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of dilated convolution…
This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists…
Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation. The significant…
Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise.…
We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…
In this paper, a low-noise CMOS image sensor with enhanced dynamic range (DR), using an in-pixel chopping technique, is presented. The proposed in-pixel chopping technique is used to reduce the low-frequency or 1/f noise of the source…
The primary aim of single-image super-resolution is to construct high-resolution (HR) images from corresponding low-resolution (LR) inputs. In previous approaches, which have generally been supervised, the training objective typically…
Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and…
As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to…
We address the two fundamental problems of spatial field reconstruction and sensor selection in het- erogeneous sensor networks. We consider the case where two types of sensors are deployed: the first consists of expensive, high quality…
We propose a novel scene-segmentation-based exposure compensation method for multi-exposure image fusion (MEF) based tone mapping. The aim of MEF-based tone mapping is to display high dynamic range (HDR) images on devices with limited…
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of different domains can be decomposed into the low-frequency…