Most neural compression models are trained on large datasets of images or
videos in order to generalize to unseen data. Such generalization typically
requires large and expressive architectures with a high decoding complexity.
Here we introduce C3, a neural compression method with strong rate-distortion
(RD) performance that instead overfits a small model to each image or video
separately. The resulting decoding complexity of C3 can be an order of
magnitude lower than neural baselines with similar RD performance. C3 builds on
COOL-CHIC (Ladune et al.) and makes several simple and effective improvements
for images. We further develop new methodology to apply C3 to videos. On the
CLIC2020 image benchmark, we match the RD performance of VTM, the reference
implementation of the H.266 codec, with less than 3k MACs/pixel for decoding.
On the UVG video benchmark, we match the RD performance of the Video
Compression Transformer (Mentzer et al.), a well-established neural video
codec, with less than 5k MACs/pixel for decoding.

C3 是一种神经压缩方法，通过对每个图像或视频进行过度拟合从而获得强大的率失真性能，其解码复杂度与其他具有相似率失真性能的神经模型相比可降低一个数量级。C3 在 COOL-CHIC 的基础上进行改进，并且还开发了将 C3 应用于视频的新方法。在 CLIC2020 图像基准测试中，我们将 C3 解码的每个像素的 MAC 数减少到不足 3k，与 H.266 编解码器的 VDH 性能相当。在 UVG 视频基准测试中，我们将 C3 解码的每个像素的 MAC 数减少到不足 5k，与 Video Compression Transformer 的 VDH 性能相当。