No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Improved Predictive Coding for Animation-Based Video Compression
... HDAC+ [52] EUVIP 2024 Exploits a dual residual learning strategy for improved GFVC performance. ...
... • Residual Coding [6], [52]: Encoding residual differences between GFVC-generated and actual frames could facilitate to preserve fine details critical for perceptual realism. This approach balances compression efficiency with visual fidelity, ensuring that subtle facial features are accurately reconstructed. ...
The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware representation and lifelike synthesis. Generative Face Video Coding (GFVC) stands at the forefront of this revolution, which could characterize complex facial dynamics into compact latent codes for bitstream compactness at the encoder side and leverages powerful deep generative models to reconstruct high-fidelity face signal from the compressed latent codes at the decoder side. As such, this well-designed GFVC paradigm could enable high-fidelity face video communication at ultra-low bitrate ranges, far surpassing the capabilities of the latest Versatile Video Coding (VVC) standard. To pioneer foundational research and accelerate the evolution of GFVC, this paper presents the first comprehensive survey of GFVC technologies, systematically bridging critical gaps between theoretical innovation and industrial standardization. In particular, we first review a broad range of existing GFVC methods with different feature representations and optimization strategies, and conduct a thorough benchmarking analysis. In addition, we construct a large-scale GFVC-compressed face video database with subjective Mean Opinion Scores (MOSs) based on human perception, aiming to identify the most appropriate quality metrics tailored to GFVC. Moreover, we summarize the GFVC standardization potentials with a unified high-level syntax and develop a low-complexity GFVC system which are both expected to push forward future practical deployments and applications. Finally, we envision the potential of GFVC in industrial applications and deliberate on the current challenges and future opportunities.
In the last 17 years, since the finalization of the first version of the now-dominant H.264/Moving Picture Experts Group-4 (MPEG-4) Advanced Video Coding (AVC) standard in 2003, two major new generations of video coding standards have been developed. These include the standards known as High Efficiency Video Coding (HEVC) and Versatile Video Coding (VVC). HEVC was finalized in 2013, repeating the ten-year cycle time set by its predecessor and providing about 50% bit-rate reduction over AVC. The cycle was shortened by three years for the VVC project, which was finalized in July 2020, yet again achieving about a 50% bit-rate reduction over its predecessor (HEVC). This article summarizes these developments in video coding standardization after AVC. It especially focuses on providing an overview of the first version of VVC, including comparisons against HEVC. Besides further advances in hybrid video compression, as in previous development cycles, the broad versatility of the application domain that is highlighted in the title of VVC is explained. Included in VVC is the support for a wide range of applications beyond the typical standard- and high-definition camera-captured content codings, including features to support computer-generated/screen content, high dynamic range content, multilayer and multiview coding, and support for immersive media such as 360° video.
Conditional coding is a new video coding paradigm enabled by neural-network-based compression. It can be shown that conditional coding is in theory better than the traditional residual coding, which is widely used in video compression standards like HEVC or VVC. However, on closer inspection, it becomes clear that conditional coders can suffer from information bottlenecks in the prediction path, i.e., that due to the data processing inequality not all information from the prediction signal can be passed to the reconstructed signal, thereby impairing the coder performance. In this paper we propose the conditional residual coding concept, which we derive from information theoretical properties of the conditional coder. This coder significantly reduces the influence of bottlenecks, while maintaining the theoretical performance of the conditional coder. We provide a theoretical analysis of the coding paradigm and demonstrate the performance of the conditional residual coder in a practical example. We show that conditional residual coders alleviate the disadvantages of conditional coders while being able to maintain their advantages over residual coders. In the spectrum of residual and conditional coding, we can therefore consider them as “the best from both worlds”.
Objective measures of image quality generally operate by comparing pixels of a “degraded” image to those of the original. Relative to human observers, these measures are overly sensitive to resampling of texture regions (e.g., replacing one patch of grass with another). Here, we develop the first full-reference image quality model with explicit tolerance to texture resampling. Using a convolutional neural network, we construct an injective and differentiable function that transforms images to multi-scale overcomplete representations. We demonstrate empirically that the spatial averages of the feature maps in this representation capture texture appearance, in that they provide a set of sufficient statistical constraints to synthesize a wide variety of texture patterns. We then describe an image quality method that combines correlations of these spatial averages (“texture similarity”) with correlations of the feature maps (“structure similarity”). The parameters of the proposed measure are jointly optimized to match human ratings of image quality, while minimizing the reported distances between subimages cropped from the same texture images. Experiments show that the optimized method explains human perceptual scores, both on conventional image quality databases, as well as on texture databases. The measure also offers competitive performance on related tasks such as texture classification and retrieval. Finally, we show that our method is relatively insensitive to geometric transformations (e.g., translation and dilation), without use of any specialized training or data augmentation. Code is available at
https://github.com/dingkeyan93/DISTS
.
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on the ImageNet classification task has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are critical for their success? To answer these questions, we introduce a new Full Reference Image Quality Assessment (FR-IQA) dataset of perceptual human judgments, orders of magnitude larger than previous datasets. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by huge margins. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.
We describe an image compression system, consisting of a nonlinear encoding transformation, a uniform quantizer, and a nonlinear decoding transformation. Like many deep neural network architectures, the transforms consist of layers of convolutional linear filters and nonlinear activation functions, but we use a joint nonlinearity that implements a form of local gain control, inspired by those used to model biological neurons. Using a variant of stochastic gradient descent, we jointly optimize the system for rate-distortion performance over a database of training images, introducing a continuous proxy for the discontinuous loss function arising from the quantizer. The relaxed optimization problem resembles that of variational autoencoders, except that it must operate at any point along the rate-distortion curve, whereas the optimization of generative models aims only to minimize entropy of the data under the model. Across an independent database of test images, we find that the optimized coder exhibits significantly better rate-distortion performance than the standard JPEG and JPEG 2000 compression systems, as well as a dramatic improvement in visual quality of compressed images.
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear filters and nonlinear activation functions. Unlike most convolutional neural networks, the joint nonlinearity is chosen to implement a form of local gain control, inspired by those used to model biological neurons. Using a variant of stochastic gradient descent, we jointly optimize the entire model for rate-distortion performance over a database of training images, introducing a continuous proxy for the discontinuous loss function arising from the quantizer. Under certain conditions, the relaxed loss function may be interpreted as the log likelihood of a generative model, as implemented by a variational autoencoder. Unlike these models, however, the compression model must operate at any given point along the rate-distortion curve, as specified by a trade-off parameter. Across an independent set of test images, we find that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods. More importantly, we observe a dramatic improvement in visual quality for all images at all bit rates, which is supported by objective quality estimates using MS-SSIM.
High Efficiency Video Coding (HEVC) is currently being prepared as the newest video coding standard of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group. The main goal of the HEVC standardization effort is to enable significantly improved compression performance relative to existing standards-in the range of 50% bit-rate reduction for equal perceptual video quality. This paper provides an overview of the technical features and characteristics of the HEVC standard.
Deep contextual video compression
- J Li
- B Li
- Y Lu
First order motion model for image animation
- A Siarohin
- S Lathuiliere
- S Tulyakov
- E Ricci
- N Sebe
Very deep convolutional networks for large-scale image recognition
- K Simonyan
- A Zisserman
- Y Bengio
- Y Lecun