A novel intra prediction method is presented in this paper, where the prediction samples are generated by an extrapolation filter. This method has been proposed for the future video coding standard. Firstly, an extrapolation filter is either derived from the reconstructed neighboring area or inherited from the neighboring decoded blocks of the current block. Secondly, the prediction samples are generated by an extrapolation process in a parallel manner. The proposed extrapolation filter-based intra prediction method is implemented on top of the exploration test model ECM-10.0 reference software, and the simulations are conducted according to the common test conditions. Compared to ECM-10.0, the simulation results show {0.24%,0.19%,0.19%} BD-rates saving for {Y,U,V} components in the all intra configuration and {0.10%,0.12%,0.19%} BD-rates saving for {Y,U,V} components in the random access configuration.

Intra template matching prediction (Intra TMP) is a promising intra prediction tool which generates the prediction block by copying from a reconstructed block of the current frame. The position of the reconstructed block is derived by template matching at both encoder and decoder. Intra TMP has been adopted in enhanced compression model (ECM) for both screen content and natural content due to its outstanding trade-off between coding efficiency and complexity. This paper describes an advanced intra TMP algorithm with fusion techniques to further improve the coding efficiency. The proposed intra TMP fusion scheme includes the following aspects: 1) extended template matching search range, 2) improved search procedure with multiple candidates, 3) adaptive fusion method with template updating, and 4) support fractional-pel precision in intra TMP. Experimental results show that the proposed intra TMP fusion scheme provides 0.76% average luma Bjøntegaard delta rate (BD-rate) reduction with negligible runtime increase over ECM-8.0 in all-intra configuration.

Augmenting large language models (LLM) to use external tools enhances their performance across a variety of tasks.However, prior works over-rely on task-specific demonstration of tool use that limits their generalizability and computational cost due to making many calls to large-scale LLMs.We introduce GEAR, a computationally efficient query-tool grounding algorithm that is generalizable to various tasks that require tool use while not relying on taskspecific demonstrations.GEAR achieves better efficiency by delegating tool grounding and execution to small language models (SLM) and LLM, respectively; while leveraging semantic and pattern-based evaluation at both question and answer levels for generalizable tool grounding.We evaluate GEAR on 14 datasets across 6 downstream tasks, demonstrating its strong generalizability to novel tasks, tools and different SLMs.Despite offering more efficiency, GEAR achieves higher precision in tool grounding compared to prior strategies using LLM prompting, thus improving downstream accuracy at a reduced computational cost.For example, we demonstrate that GEAR-augmented GPT-J and GPT-3 outperform counterpart toolaugmented baselines because of better tool use.

A set of auto encoders is trained to perform intra prediction for block-based video coding. Each auto encoder consists of an encoding network and a decoding network. Both encoding network and decoding networks are jointly optimized and integrated into the state-of-the-art VVC reference software VTM-11.0 as an additional intra prediction mode. The simulation is conducted under common test conditions with all intra config-urations and the test results show 1.55%, 1.04%, and 0.99% of Y, U, V components Bjentegaard-Delta bit rate saving compared to VTM-11.0 anchor, respectively. The overall relative decoding running time of proposed autoencoder-based intra prediction mode on top of VTM-11.0 are 408% compared to VTM-11.0.

This paper presents a low-complexity lossless screen content coding method on top of a well structured dictionary based solution DictSCC. Both methods are implemented on the emerging High-Efficiency Video Coding (HEVC) Range Extensions (RExt) to demonstrate the coding efficiency. Compared with the DictSCC our scheme further explores the 2D correlation between neighboring image blocks for performance improvement, and reduces the complexity significantly by constraining the dictionary buffer which will be more favored by the hardware implementation. Results demonstrate averaged 17%, 10% and 8% bit rate reduction over HEVC for screen content compression with respect to All Intra, Random Access and Low-Delay encoder configurations.

This paper presents an advanced screen content coding solution using color table and index map (cTIM) method. This cTIM scheme is implemented in the range extensions of high-efficiency video coding (HEVC-RExt) as an additional tool of intracoding to complement conventional spatial angular prediction to better exploit the screen content redundancy. For each coding unit, a number of major colors will be selected to form the color table, then the original pixel block is translated to the corresponding index map. A 1D or hybrid 1D/2D string match scheme is introduced to derive matched pairs of index map for better compression. Leveraging the color distribution similarity between neighboring image blocks, color table merge is developed to carry it implicitly. For those blocks that color table has to be signaled explicitly, intertable color sharing and intratable color differential predictive coding are applied to reduce the signaling overhead. Extensive experiments have been performed and they have demonstrated the significant coding efficiency improvement over conventional HEVC-RExt, resulting in 26%, 18%, and 15% bit rate reduction at lossless case and 23%, 19%, and 13% Bjontegaard Delta-rate improvement at lossy scenario of typical screen content with text and graphics, for respective all intra, random access, and low-delay using B picture encoder settings. Detailed performance study and complexity analysis (as well as the comparison with other algorithms) have been included as well to evidence the efficiency of proposed algorithm.

The lossless coding mode of the High Efficiency Video Coding (HEVC) main profile that bypasses transform, quantization, and in-loop filters is described. Compared to the HEVC nonlossless coding mode with the smallest quantization parameter value (i.e., 0 for 8-b video and -12 for 10-b video), the HEVC lossless coding mode provides perfect fidelity and an average bit-rate reduction of 3.2%-13.2%. It also significantly outperforms the existing lossless compression solutions, such as JPEG2000 and JPEG-LS for images as well as 7-Zip and WinRAR for data archiving. To further improve the coding efficiency of the HEVC lossless mode, a sample-based angular intra prediction (SAP) method is presented. The SAP employs the same prediction mode signaling method and the sample interpolation method as the HEVC block-based angular prediction, but uses adjacent neighbors for better intra prediction accuracy and performs prediction sample by sample. The experimental results reveal that the SAP provides an additional bit-rate reduction of 1.8%-11.8% on top of the HEVC lossless coding mode.

To support high quality video applications, the Joint Video Team (JVT) has recently added five new profiles, two new supplemental enhancement information (SEI) messages, and two new extended gamut color space indicators to the MPEG4-AVC/H.264 video coding standard. The new profiles include substantial feature enhancements for high-quality video applications, including improved-efficiency 4:4:4 video format coding, improved-efficiency lossless macroblock coding, coding 4:4:4 video pictures using three separately-coded color planes, and support of bit depths up to 14 bits per sample. The new features were developed to support a wide range of applications where high quality video compression is demanded, including professional and semi-professional scenarios in particular. They also anticipate the introduction of higher fidelity displays. In this paper, the new extensions are presented along with quantitaive estimates of the benefits of the new features and a discussion of the target application environments.

In this paper, we describe an adaptive lossless compression algorithm for color video sequences utilizing backward adaptive temporal prediction and an integer wavelet transform. We exploit two redundancies in color video sequences, specifically spatial and temporal redundancies. We show that an adaptive scheme exploiting the two redundancies has better compression performance than lossless compression of individual image frames. The result of the proposed scheme is compared to current video compression algorithms.

A linear technique for two-dimensional (2D), frequency domain, system modeling has been successfully developed by W.B. Mikhael and H. Yu (1993). Based on the same structure, which is the equation error model, a two-dimensional least-square spectral representation algorithm is presented in this paper. The proposed algorithm efficiently characterizes the 2D complex spectra by a 2D all-pole function with real coefficients. The location, magnitude and phase of the dominant transform components can be exactly retrieved in the 2D frequency domain. It is shown that the number of coefficients of the approximating function is (2M+1), where M is the number of dominant transform components. To illustrate the technique's accuracy and efficieny its application to image representation and reconstruction is given.>