“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The PASCAL Visual Object Classes Challenge

The compression capability of several generations of video coding standards is compared by means of peak signal-to-noise ratio (PSNR) and subjective testing results. A unified approach is applied to the analysis of designs, including H.262/MPEG-2 Video, H.263, MPEG-4 Visual, H.264/MPEG-4 Advanced Video Coding (AVC), and High Efficiency Video Coding (HEVC). The results of subjective tests for WVGA and HD sequences indicate that HEVC encoders can achieve equivalent subjective reproduction quality as encoders that conform to H.264/MPEG-4 AVC when using approximately 50% less bit rate on average. The HEVC design is shown to be especially effective for low bit rates, high-resolution video content, and low-delay communication applications. The measured subjective improvement somewhat exceeds the improvement measured by the PSNR metric.

http://amalia.img.lx.it.pt/~fp/cav/Additional_material/HEVC-Performance.pdf

Comparison of the Coding Efficiency of Video Coding Standards—Including High Efficiency Video Coding (HEVC)

We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss. DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem - object detection on (de-)blurred images. The method is 5 times faster than the closest competitor - Deep-Deblur [25]. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN

/pdf/deblurgan-blind-motion-deblurring-using-conditional-150wx51y9w.pdf

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics to no-reference metrics and to subjective evaluation, and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of the state-of-the-art dehazing algorithms, and suggest promising future directions.

Benchmarking Single-Image Dehazing and Beyond

The application relates to an intra block copy mode with dual tree partition. A method of video processing is disclosed. The method of video processing includes: determining, during a conversion between a current video block and a bitstream representation of the current video block, a block vector for the current video block; and performing, at least based on the block vector, the conversion, wherein when the current video block is coded with a coding mode using a reference block for prediction pointing to a same picture that the current video block is located in, and the current video block is a first type of block, the block vector is derived from at least one second type of block.

Intra block copy mode with dual tree partition

Adaptive resolution change and scalable coding for screen contents are described. One example is a method for video processing, comprising: determining, for a conversion between a picture or a video and a bitstream representation of the picture or the video, whether the picture or the video is native resolution based on an indication included in the bitstream representation; and performing the conversion based on the determination.

Adaptive resolution change and scalable coding for screen contents

Compound triple tree in video coding is described. In an exemplary aspect, a method for video processing includes determining, for a conversion between a first block of video and a bitstream representation of the first block of video, whether Compound Triple-Tree (CTT) partition is enabled or disabled, wherein CTT partition includes splitting the first block to nine smaller sized sub-blocks of the first block; and performing the conversion based on the determination.

Compound triple tree in video coding

A method for video bitstream processing includes generating, using a first video block derived from a third video block of a first component and having a first size, a prediction block for a second video block of a video related to a second component, where the first component is different from the secondcomponent, and where the second video block has a second size that is different from the first size. The method also includes performing, using the prediction block, a conversion between the second video block and a bitstream representation of the video according to a two-step cross-component prediction mode (TSCPM).

Two step cross-component prediction mode

A method of video processing is described. The method includes: determining, based on a coding mode of a current video block of a video, whether a position dependent intra prediction combination (PDPC) method is used for coding the current video block based on a first rule, and performing a conversion between the current video block and a coded representation of the video according to the determining, wherein the PDPC method combines neighboring samples with a prediction signal of the current video block to generate a refined prediction signal of the current video block.

Xu Jizheng

Papers

Intra block copy mode with dual tree partition

Adaptive resolution change and scalable coding for screen contents

Compound triple tree in video coding

Two step cross-component prediction mode

Position-dependent intra prediction sample filtering