Flexible Neural Image Compression via Code Editing
Neural image compression (NIC) has outperformed traditional image codecs in rate-distortion (R-D) performance. However, it usually requires a dedicated encoder-decoder pair for each point on R-D curve, which greatly hinders its practical deployment. While some recent works have enabled bitrate control via conditional coding, they impose strong prior during training and provide limited flexibility. In this paper we propose Code Editing, a highly flexible coding method for NIC based on semi-amortized inference and adaptive quantization. Our work is a new paradigm for variable bitrate NIC. Furthermore, experimental results show that our method surpasses existing variable-rate methods, and achieves ROI coding and multi-distortion trade-off with a single decoder.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderImage CompressionQuantizationSimilar Papers 제목 키워드 기반
GaINeR: Geometry-Aware Implicit Network Representation
Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate…
Image ManipulationImage EditingStyle Transformer for Image Inversion and Editing
Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleG…
AttributeImage-to-Image TranslationBetter Compression with Deep Pre-Editing
Could we compress images via standard codecs while avoiding visible artifacts? The answer is obvious -- this is doable as long as the bit budget is generous enough. What if the allocated bit-rate for compression is insuf…
Improving Multi-generation Robustness of Learned Image Compression
Benefit from flexible network designs and end-to-end joint optimization approach, learned image compression (LIC) has demonstrated excellent coding performance and practical feasibility in recent years. However, existing…
Image CompressionQuantizationLearning to Improve Image Compression without Changing the Standard Decoder
In recent years we have witnessed an increasing interest in applying Deep Neural Networks (DNNs) to improve the rate-distortion performance in image compression. However, the existing approaches either train a post-proce…
DecoderImage CompressionMS-SSIMQuantization+1