Fast Training-free Perceptual Image Compression
By: Ziran Zhu , Tongda Xu , Minye Huang and more
Potential Business Impact:
Makes pictures look better, faster, without retraining.
Training-free perceptual image codec adopt pre-trained unconditional generative model during decoding to avoid training new conditional generative model. However, they heavily rely on diffusion inversion or sample communication, which take 1 min to intractable amount of time to decode a single image. In this paper, we propose a training-free algorithm that improves the perceptual quality of any existing codec with theoretical guarantee. We further propose different implementations for optimal perceptual quality when decoding time budget is $\approx 0.1$s, $0.1-10$s and $\ge 10$s. Our approach: 1). improves the decoding time of training-free codec from 1 min to $0.1-10$s with comparable perceptual quality. 2). can be applied to non-differentiable codec such as VTM. 3). can be used to improve previous perceptual codecs, such as MS-ILLM. 4). can easily achieve perception-distortion trade-off. Empirically, we show that our approach successfully improves the perceptual quality of ELIC, VTM and MS-ILLM with fast decoding. Our approach achieves comparable FID to previous training-free codec with significantly less decoding time. And our approach still outperforms previous conditional generative model based codecs such as HiFiC and MS-ILLM in terms of FID. The source code is provided in the supplementary material.
Similar Papers
All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perception
CV and Pattern Recognition
Makes one AI model understand many image tasks.
Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation
CV and Pattern Recognition
Makes AI create pictures and videos much faster.
Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization
Machine Learning (CS)
Makes picture files smaller with better quality.