The super-resolution (SR)-based coding tool is widely employed in modern video coding standards. By encoding video frames at a reduced resolution and then restoring them to their original resolution during the in-loop filtering stage, this tool helps to further reduce the bitrate and improve the coding performance. Current video coding standards typically devise rule-based SR methods in their codecs, compromising the coding efficiency to maintain low computational complexity. As deep neural network (DNN)-based SR methods are proving more effective than rule-based approaches, this paper proposes integrating the neural SR into video codecs to enhance coding performance while minimizing the computational cost. To this end, we propose a Lightweight Implicit Neural Model (LIM). Specifically, our LIM, consisting of Lightweight Feature Aggregation Network (LFANet) and Coordinate Upsampling Network Based on B-spline Representation (CURNet), is developed to support SR-based coding at an arbitrary scale. We exemplify the proposed method on the ongoing AVM reference software and conduct extensive experiments to demonstrate its effectiveness. Compared with anchored AVM, our method improves the BD-Rate by 5.52%, which significantly outperforms state-of-the-art works. Meanwhile, its computational complexity is much lower than others, having only 22.5k parameters and 18.7k FLOPs/pixel complexity, which is attractive to real-world applications.

We present a standard-compatible video coding scheme with end-to-end optimized neural wrapper over standard video codecs that achieves significant rate-distortion (R-D) performance gains and is still efficient in decoding. We train a pair of pre- and post-processor using a differential JPEG proxy. The pre-processor applies a learned transform to the video and downsamples the video by a factor of 2. It generates a bottleneck video to be coded by a standard codec as a YUV sequence. The post-processor takes the decoded bottleneck video, does the inverse transform, and upsamples it to the original resolution. We follow the design in [1] , where we configure downsample using a layer of strided convolution. We optimize the post-processor for efficiency by replacing convolutions with kernel size larger than 1×1 to depth-wise convolutions [2] .

This paper proposes a multi-layer multi-reference prediction framework for effective video compression. Current AOM/AV1 baseline uses three reference frames for the inter prediction of each video frame. This paper first presents a new coding tool that extends the total number of reference frames in both forward and backward prediction directions. A multi-layer framework is then described, which suggests the encoder design and places different reference frames within one Golden Frame (GF) group to different layers. The multi-layer framework leverages the existing coding tools in the AV1 baseline, including the tool of "show_existing_frame" and the reference frame buffer update module of a wide flexibility. The use of extended ALTREF_FRAMEs is proposed, and multiple ALTREF_FRAME candidates are selected and widely spaced within one GF group. ALTREF_FRAME is a constructed, no-show reference obtained through temporal filtering of a look-ahead frame. In the multi-layer structure, one reference frame may serve different roles for the encoding of different frames through the virtual index manipulation. The experimental results have been collected over several video test sets of various resolutions and characteristics both texture- and motion-wise, which demonstrate that the proposed approach achieves a consistent coding gain compared to the AV1 baseline. For instance, using PSNR as the distortion metric, an average bitrate saving of 5.57+% in BDRate is obtained for the CIF-level resolution set, some of which has a gain of up to 13+%, and 4.47% on average for the VGA-level resolution set, some of which up to 18+%.