机会性条件熵编码：冻结分析与合成变换
Opportunistic Conditional Entropy Coding with Frozen Analysis and Synthesis Transforms
- Mitsubishi Electric R&D Centre Europe（三菱电机欧洲研发中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出一种机会性条件熵编码方法，利用可能存在的边信息降低码率，同时冻结分析与合成变换以兼容现有编解码器，最高可节省52%码率且无边信息时损失低于4%。
AI中文摘要：
在许多传输场景中，接收方可能已经通过独立传输获得了图像的较低质量或较低分辨率表示。传统编解码器在编码随后请求的较高质量表示时，不会利用这种偶然的边信息，而条件编解码器通常假设存在一种始终可用的规定边信息源。我们转而考虑一种机会性场景，其中边信息可能存在也可能不存在。我们引入了一个单一的熵模型，当先前解码的潜变量可用时，该模型以其为条件，否则回退到标准的超先验。所提出的适配器将边信息潜变量映射到熵模型所需的先验信号，使得同一模型能够支持多种目标与边信息质量组合。分析和合成变换保持冻结，从而能够对现有学习编解码器进行改造，同时保留其潜变量表示和重建路径。当接收方持有紧邻目标之下的质量时，所提出的方法将后续传输的码率降低高达46%，若额外传输超潜变量则降低52%。在没有边信息的情况下，码率损失保持在4%以下，且条件模式与回退模式下的重建结果逐位相同。
英文摘要：
In many delivery settings, a receiver may already hold a lower-quality or lower-resolution representation of an image, obtained through an independent transmission. Conventional codecs encode a subsequently requested higher-quality representation without exploiting this incidental side information, whereas conditional codecs generally assume a prescribed source of side information that is always available. We instead consider an opportunistic setting in which side information may or may not be present. We introduce a single entropy model that conditions on a previously decoded latent when available and falls back to a standard hyperprior otherwise. The proposed adapter maps the side-information latent to the prior signal required by the entropy model, allowing the same model to support multiple target and side-information quality combinations. The analysis and synthesis transforms remain frozen, enabling retrofitting of an existing learned codec while preserving its latent representation and reconstruction path. When the receiver holds the quality immediately below the target, the proposed method reduces the rate of the subsequent transmission by up to 46%, or by 52% when an additional hyper-latent is transmitted. In the absence of side information, the rate penalty remains below 4%, and the reconstructions are bit-identical across the conditional and fallback modes.
