Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.

SFSRNet: Super-resolution for Single-Channel Audio Source Separation

Abstract: The problem of single-channel audio source separation is to recover (separate) multiple audio sources that are mixed in a single-channel audio signal (e.g. people talking over each other). Some of the best performing single-channel source separation methods utilize downsampling to either make the separation process faster or make the neural networks bigger and increase accuracy. The problem concerning downsampling is that it usually results in information loss. In this paper, we tackle this problem by introducing SFSRNet which contains a super-resolution (SR) network. The SR network is trained to reconstruct the missing information in the upper frequencies of the audio signal by operating on the spectrograms of the output audio source estimations and the input audio mixture. Any separation method where the length of the sequence is a bottleneck in speed and memory can be made faster or more accurate by using the SR network. Based on the WSJ0-2mix benchmark where estimations of the audio signal of two speakers need to be extracted from the mixture, in our experiments our proposed SFSRNet reaches a scale-invariant signal-to-noise-ratio improvement (SI-SNRi) of 24.0 dB outperforming the state-of-the-art solution SepFormer which reaches an SI-SNRi of 22.3 dB.

Digital camera with downsampling and zoom processing and method of controlling operation of same

Abstract: A CCD is driven so as to output a video signal at a rate of one line out of four up to an enlargement ratio of 2×. If the enlargement ratio of 2× is surpassed, the CCD is controlled so as to output a video signal at a rate of one line out of two. Since resolution of the image represented by the video signal output from the CCD is raised, an image having a comparatively high resolution is obtained even when the image is enlarged by an electronic zoom function.

SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering

Abstract: Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth. To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images. Specifically, we first propose a neighbor expansion unit (NEU) to upsample the sparse point clouds, where the local geometric structures of the sparse point clouds are exploited to learn weights for point interpolation. Then, we develop a differentiable point cloud rendering unit (DRU) as an end-to-end module in our network to render the point cloud into multi-view images. Finally, we formulate a shape-consistent loss and an image-consistent loss to train the network so that the shapes of the sparse and dense point clouds are as consistent as possible. Extensive results on the CAD and scanned datasets demonstrate that our method can achieve impressive results in a self-supervised manner.

Dynamic Depth of Field on Live Video Streams: A Stereo Solution

Abstract: The ability to produce dynamic Depth of Field effects in live video streams was until recently a quality unique to movie cameras. In this paper, we present a computational camera solution coupled with real-time GPU processing to produce runtime dynamic Depth of Field effects. We first construct a hybrid-resolution stereo camera with a high-res/low-res camera pair. We recover a low-res disparity map of the scene using GPU-based Belief Propagation and subsequently upsample it via fast Cross/Joint Bilateral Upsampling. With the recovered high-resolution disparity map, we warp the high-resolution video stream to nearby viewpoints to synthesize a light field towards the scene. We exploit parallel processing and atomic operations on the GPU to resolve visibility when multiple pixels warp to the same image location. Finally, we generate dynamic Depth of Field effects from the synthesized light field rendering. All processing stages are mapped onto NVIDIA’s CUDA architecture. Our system can produce Depth of Field effects with arbitrary aperture sizes and focal depths for the resolution of 640×480 at 15 fps.