Leveraging the generative power of diffusion models, generative image compression has achieved impressive perceptual fidelity even at extremely low bitrates. However, current methods often neglect the non-uniform complexity of images, limiting their ability to balance global perceptual quality with local texture consistency and to allocate coding resources efficiently. To address this, we introduce the Map-guided Masking Realism Image Diffusion Codec (MRIDC), designed to optimize the trade- off between local distortion and global perceptual quality in extreme-low bitrate compression. MRIDC integrates a vector-quantized image encoder with a diffusion-based decoder. On the encoding side, we propose a Map-guided Latent Masking (MLM) module, which selectively masks elements in the latent space based on prior information, allowing adaptive resource allocation aligned with image complexity. On the decoding side, masked latents are completed using the Bidirectional Prediction Controllable Generation (BPCG) module, which guides the constrained generation process within the diffusion model to reconstruct the image. Experimental results show that MRIDC achieves state-of-the-art perceptual compression quality at extremely low bitrates, effectively preserving feature consistency in key regions and advancing the rate-distortion-perception performance curve, establishing new benchmarks in balancing compression efficiency with visual fidelity. Our code can be found at https://github.com/xjc97/mridc.

The introduction of multiple transform types in the Versatile Video Coding (VVC) standard has yielded notable encoding gains but also imposed considerable computational burdens. Existing transform circuits of different types are typically implemented separately due to their independence, leading to substantial hardware overhead. To address this, we explore the relationship between Discrete Cosine Transform Type-2 (DCT2) and Discrete Sine Transform Type-7 (DST7) matrices and reveal a prominent diagonal aggregation phenomenon in their transfer matrix. Based on this insight, the least-squares method is applied to optimize the transfer matrix sparsity, achieving a high-precision, low-cost approximate conversion from DCT2 to DST7. Furthermore, we optimize DCT2 computation by proposing an elaborate matrix decomposition approach that allows a lightweight shift-adder unit to efficiently generate all required product terms across varying sizes. Leveraging these algorithmic optimizations, we implement a highly reusable and area-efficient approximate transform accelerator that supports sizes from 4 to 32 points and accommodates three types in VVC. Experimental results demonstrate that the proposed accelerator achieves over 44% reduction in circuit resource consumption with negligible BD-BR performance loss of just $\mathbf{0. 5 3 \%}$, maintaining processing capabilities up to $8 K \text{@} 57 \mathrm{fps}$.

Neural image compression has achieved significant advancements, consistently outperforming traditional codecs in terms of performance. However, research on quality control algorithms for neural image compression is still lacking. In this paper, we propose a framework designed to control the quality of compressed images through a one-pass pre-analysis. First, we construct a foundational relationship between the quantization factor and compression distortion, utilizing variable rate neural image compression as the basis for quality control. Second, we introduce the image Content-Compression features-based Distortion Estimation Network (C2DEN) to efficiently fit the sample-adaptive Quantization-Distortion (QD) model. Leveraging the QD model, we convert the target quality into a quantization factor to control the compression model, enabling quality-controllable compression of samples. Experimental results show that the average quality errors on four different datasets are only 0.89%, 1.79%, 1.73%, and 1.61%. Compared with existing control methods, our method reduces the algorithm time complexity by 98.58%, 98.52%, 98.85%, and 98.50% while ensuring accuracy, which further demonstrates the superiority of our method.

With the development of visual analysis models, collaborative image compression for machine and human perception has brought new challenges to the optimization of algorithms. Existing optimization algorithms achieve this target through meticulously designed model structures and bitstream design. However, the difference in bitstream design makes it incompatible with trained and existing decoders, hindering its practicality. In this paper, we proposed the Adaptive Semantic Compression (ASC) framework to fine-tune pre-trained codec on individual samples to obtain scalable bitstreams in an intuitive yet effective way. First, to improve the efficiency of application in machine perception, we proposed the Latent Semantic Contraction (LSC) method to fine-tune the latent code while preserving the machine task performance of the decoded image. Second, to further optimize human perception, we proposed the Spatial-frequency Decoder Adaptation (SFDA) module. By compensating for distortion in the spatial and frequency domains, SFDA improves the humane perception quality of the reconstructed image. The bitstreams composed of LSC and SFDA can be decoded by existing decoders to reconstruct images, thus fully exploiting the performance of the existing model. We implemented our algorithm on different pre-trained compression models and verified the flexibility and compatibility on various test images. Experimental results show that the LSC module can save 24.97% to 29.10% of bitrates with machine perception performance. Furthermore, the application of SFDA brings a 3.16% gain in the BD-Rate with PSNR, up to 15.69%, compared to LSC.

The introduction of multiple transform types into the Versatile Video Coding (VVC) standard has yielded notable encoding gains but also resulted in substantial computational burdens, posing two critical challenges for hardware implementation: fast kernel selection and efficient transform computation design. Existing studies typically address these challenges in isolation, lacking a holistic solution for VVC transform coding. In this paper, we presents a groundbreaking transform accelerator that unifies transform kernel selection and multiple transform circuit within a single framework. In terms of algorithms, driven by mechanistic analysis, we propose a decision tree-based kernel selection algorithm that ensures both high decision accuracy and computational efficiency. Additionally, we design a transfer matrix-based approximation algorithm for Discrete Sine Transform Type-7 and a matrix decomposition-based improved computation for Discrete Cosine Transform Type-2, significantly reducing the computational complexity. On the hardware front, we implement a high-precision and area-efficient transform accelerator, which integrates highly pipelined kernel selection and transform computation architectures. With multiple reuse and parallelism strategies, the accelerator demonstrates substantial resource efficiency advantages. Experimental results reveal that the proposed accelerator achieves a circuit resource reduction of over 44% with a slight performance degradation, while maintaining processing capabilities up to 8K@57 fps. To the best of our knowledge, this is the first comprehensive hardware solution for VVC transform coding that jointly addresses the challenges of kernel selection and transform circuit design.

In this paper, we present a video-based emotion recognition system in the wild which consists of four pipeline modules: image-processing, deep feature extraction, feature aggregation and emotion classification. Our method focuses more on different feature descriptors. To obtain high-level features which are more discriminative in emotion recognition, we employ an aggregation of features extracted from different deep convolutional neural networks (CNNs). Furthermore, the long short-term memory network (LSTM) and 3D convolutional networks (C3D) are utilized to extract spatio-temporal features from videos in order to combine the spatial information and temporal information. Additionally, we evaluate our method on the 5th Emotion Recognition in the Wild Challenge in the category of video-based emotion recognition and the result shows our proposed system achieves better performance.