Preprocessing is a well-established technique for optimizing compression, yet existing methods are predominantly Rate-Distortion (R-D) optimized and constrained by pixel-level fidelity. This work pioneers a shift towards Rate-Perception (R-P) optimization by, for the first time, adapting a large-scale pre-trained diffusion model for compression preprocessing. We propose a two-stage framework: first, we distill the multi-step Stable Diffusion 2.1 into a compact, one-step image-to-image model using Consistent Score Identity Distillation (CiD). Second, we perform a parameter-efficient fine-tuning of the distilled model's attention modules, guided by a Rate-Perception loss and a differentiable codec surrogate. Our method seamlessly integrates with standard codecs without any modification and leverages the model's powerful generative priors to enhance texture and mitigate artifacts. Experiments show substantial R-P gains, achieving up to a 30.13% BD-rate reduction in DISTS on the Kodak dataset and delivering superior subjective visual quality.

Generative face video coding (GFVC) is vital for modern applications like video conferencing, yet existing methods primarily focus on video motion while neglecting the significant bitrate contribution of audio. Despite the well-established correlation between audio and lip movements, this cross-modal coherence has not been systematically exploited for compression. To address this, we propose an Audio-Visual Cross-Modal Compression (AVCC) framework that jointly compresses audio and video streams. Our framework extracts motion information from video and tokenizes audio features, then aligns them through a unified audio-video diffusion process. This allows synchronized reconstruction of both modalities from a shared representation. In extremely low-rate scenarios, AVCC can even reconstruct one modality from the other. Experiments show that AVCC significantly outperforms the Versatile Video Coding (VVC) standard and state-of-the-art GFVC schemes in rate-distortion performance, paving the way for more efficient multimodal communication systems.

Adaptive video streaming requires efficient bitrate ladder construction to meet heterogeneous network conditions and end-user demands. Per-title encoding optimization typically traverses numerous encoding parameters to search the Pareto-optimal operating points for each video. Recently, researchers have attempted to predict the content-optimized bitrate ladder for pre-encoding overhead reduction [1] . However, as shown in Fig. 1 , current methods actually estimate the optimal encoding parameters that lie on the Pareto front and thus still require subsequent pre-encodings.

There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics, overlooking the heightened demands posed by machine vision systems. In this paper, we propose a video preprocessing framework tailored for machine vision tasks to address this challenge. The proposed method incorporates a neural preprocessor which retaining crucial information for subsequent tasks, resulting in the boosting of rate-accuracy performance. We further introduce a differentiable virtual codec to provide constraints on rate and distortion during the training stage. We directly apply widely used standard codecs for testing. Therefore, our solution can be easily applied to real-world scenarios. We conducted extensive experiments evaluating our compression method on two typical downstream tasks with various backbone networks. The experimental results indicate that our approach can save over 15% of bitrate compared to using only the standard codec anchor version.

We propose a practical downsampling compression scheme, as shown in Fig 1, to use a neural network as a pre-processing module for traditional codecs to improve compression performance. Specifically, we propose a neural network-based pre-processing method to improve video compression performance by downsampling high-resolution videos. Our method, called the rate-guided arbitrary rescaling network (RARN), uses a pre-trained entropy module [1] to estimate bitrate and guide the sampling process. We also use a transformer-based virtual codec (TVC) to simulate the performance of traditional codecs, using a swing-transformer-based invertible neural network to learn distortion from standard codecs, and the cyclic shift attention [2] in the network can approximate the prediction modes of HEVC. Our method, which is compatible with standard codecs (HEVC and VVC), performs well in various sampling ratios according to experimental results.