Sorry, you need to enable JavaScript to visit this website.

With the advent of deep learning, convolutional neural networks have solved many imaging problems to a large extent. However, it remains to be seen if the image “bottleneck” can be unplugged by harnessing complementary sources of data. In this paper, we present a new approach to image aesthetic evaluation that learns both visual and textual features simultaneously. Our network extracts visual features by appending global average pooling blocks on multiple inception modules (MultiGAP), while textual features from associated user comments are learned from a recurrent neural network.

This study presents a pseudo reversible symmetric extension (P-RevSE) that solves the signal boundary problem of lifting-based nonlinear-phase paraunitary filter banks (L-NLPPUFBs), which have high compression rates thanks to their not having a constraint on the linear-phase property unlike the existing transforms used in image coding standards. The conventional L-NLPPUFBs with a periodic extension (PE) yield annoying artifacts at the signal boundaries.

The quantization parameter (QP) value and Lagrangian multiplier (λ) are the key factors for an encoder to achieve the trade-off between visual quality and bit-rate in next generation multimedia communications. In this work, we propose a novel temporal redundancy ratio (TRR) model to determinate hierarchical QPs.

State-of-the-art video coding techniques employ block-based
illumination compensation to improve coding efficiency. In
this work, we propose a Lifting-based Illumination Adaptive
Transform (LIAT) to exploit temporal redundancy among
frames that have illumination variations, such as the frames
of low frame rate video or multi-view video. LIAT employs
a mesh-based spatially affine model to represent illumination
variations between two frames. In LIAT, transformed frames
are jointly compressed, together with illumination information,

Computational aesthetics have seen much progress in recent years with the increasing popularity of deep learning methods. In this paper, we present two approaches that leverage on the benefits of using Global Average Pooling (GAP) to reduce the complexity of deep convolutional neural networks. The first model fine-tunes a standard CNN with a newly introduced GAP layer. The second approach extracts global and local CNN codes by reducing the dimensionality of convolution layers with individual GAP operations.

Here we present improvements to a dynamic texture synthesis approach which is based on motion distribution statistics, able to produce high visual quality of synthesised dynamic textures. The aim is to recreate synthetically highly textured regions like water, leaves and smoke, instead of processing them with a conventional codec such as HEVC. The method involves two steps: analysis, where motion distribution statistics are computed, and synthesis, where the texture region is synthesized. Dense optical flow is utilized for estimating the random motion of dynamic textures.

Light field (LF) imaging captures multiple intensities and directions of light per pixel during acquisition in a 3D scene, so that novel images of different viewpoints or focal points can be synthesized. However, transmitting all LF data before viewer observation incurs a large startup delay. To avoid such delay, we propose a new interactive LF streaming framework, where a client periodically requests viewpoint images, and in response a server synthesizes and transmits each requested image as a carefully chosen sparse linear combination of sub-aperture images.

Over recent years there have been several efforts which aim to standardise a royalty-free video codec, such as Thor developed by Cisco, and AV1 developed by the Alliance for Open Media. In this paper we discuss how some compression tools in Thor were integrated into the emerging AV1 codec aiming to increase compression efficiency as well as to decrease computational complexity.