Generative Compression
This addresses the problem of inefficient and error-prone compression for image and video data, though it is incremental as it builds on existing generative models.
The paper tackles the limitations of traditional image and video compression by proposing generative compression, which uses generative models to achieve more accurate and visually pleasing reconstructions at deeper compression levels and demonstrates orders-of-magnitude greater resilience to bit errors compared to traditional schemes.
Traditional image and video compression algorithms rely on hand-crafted encoder/decoder pairs (codecs) that lack adaptability and are agnostic to the data being compressed. Here we describe the concept of generative compression, the compression of data using generative models, and suggest that it is a direction worth pursuing to produce more accurate and visually pleasing reconstructions at much deeper compression levels for both image and video data. We also demonstrate that generative compression is orders-of-magnitude more resilient to bit error rates (e.g. from noisy wireless channels) than traditional variable-length coding schemes.