“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

A method for processing a video includes maintaining one or more tables, wherein each table includes motion candidates derived from previously processed video blocks that are processed prior to a first video block of a video; deriving motion information for the first video block; applying refinement to the motion information when at least one decoder side motion vector derivation (DMVD) technologies is enabled; performing a conversion between a bitstream representation of the first video block and the first video block using the refined motion information; and determining, whether to use the refined motion information or un-refined motion information for updating one or more tables.

Updating of history based motion vector prediction tables

A method of visual media processing includes determining, for a conversion between a current video block of visual media data and a bitstream representation of the current video block, a buffer that stores reference samples for prediction in an intra block copy mode; for a sample spatially located at location of the current video block relative to an upper-left position of a coding tree unit including the current video block and having a block vector, computing a corresponding reference in the buffer at a reference location, wherein the reference location is determined using the block vector and the location; and upon determining that the reference location lies outside the buffer, re-computing the reference location based at least in part on a location of the current video block relative to the coding tree unit including the current video block.

Implementation aspects in intra block copy in video coding

A method for video processing, includes generating a pair-wise average merge candidate based on at least one available set of motion information; inserting the pair-wise average merge candidate into a merge candidate list for a current video block; and performing a conversion between the current video block and a bitstream representation of the current video block using the merge candidate list.

Improvement on motion candidate list construction

A method of video processing is provided to comprise: generating, for a conversion between a current video block of a video and a coded representation of the video, a first motion candidate based on one or more motion candidates in a motion candidate list and one or more interpolation filters associated with the one or more motion candidates; wherein an interpolation filter is assigned to the first motion candidate according to a rule that depends on the one or more interpolation filters associated with the one or more motion candidates; inserting the first motion candidate into the motion candidate list; and performing the conversion based on the motion candidate list.

Indication of half-pel interpolation filters in inter coding mode

A method for video bitstream processing includes generating, at least using a plurality of samples of a first video block, a prediction sample of one sample in a second video block related to a first component (1702), where the prediction sample is generated by applying a multiple parameter model that the sample of the second video block is associated with, to the plurality of samples of the first video block, and performing a conversion between the second video block and a bitstream representation of the video using the prediction sample (1704).

Xu Jizheng

Papers

Updating of history based motion vector prediction tables

Implementation aspects in intra block copy in video coding

Improvement on motion candidate list construction

Indication of half-pel interpolation filters in inter coding mode

Two step cross-component prediction mode based on multiple parameter