By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However, previous methods do not explicitly control how much detail is synthesized, which results in a common criticism of these methods: users might be worried that a misleading reconstruction far from the input image is generated. In this work, we alleviate these concerns by training a decoder that can bridge the two regimes and navigate the distortion-realism trade-off. From a single compressed representation, the receiver can decide to either reconstruct a low mean squared error reconstruction that is close to the input, a realistic reconstruction with high perceptual quality, or anything in between. With our method, we set a new state-of-the-art in distortion-realism, pushing the frontier of achievable distortion-realism pairs, i.e., our method achieves better distortions at high realism and better realism at low distortion than ever before.

我们展示了如何使用变压器来大大简化神经视频压缩。以前的方法一直依赖越来越多的建筑偏见和先进的方法，包括运动预测和翘曲操作，从而产生复杂的模型。取而代之的是，我们独立地将输入帧映射到表示形式，并使用变压器对其依赖性进行建模，让它预测给定过去的未来表示的分布。最终的视频压缩变压器优于标准视频压缩数据集上的先前方法。合成数据的实验表明，我们的模型学会了处理复杂的运动模式，例如纯粹从数据中模糊和褪色。我们的方法易于实施，我们发布代码以促进未来的研究。

我们介绍了基于生成的对抗性网络（GANS）的第一神经视频压缩方法。我们的方法显着优于用户研究中的先前神经和非神经视频压缩方法，为神经方法的视觉质量设置新的最先进。我们表明GaN亏损至关重要，以获得这种高视觉质量。两个组件使GaN丢失有效：我们）通过调节从翘曲的先前的重建提取的潜伏的发电机来合成细节，然后II）以高质量的流传播该细节。我们发现，用户学习必须比较方法，即，我们的定量指标都无法预测所有研究。我们详细展示了网络设计选择，并通过用户研究消除了它们。