Skip to content
Preprint

Multi-scale Image Representation Compression

Sep 2026 · 0 citations · 30 references
Engineering Computer Science

TL;DR

MIRC is proposed, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC.

Abstract

Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at the cost of a longer overfitting process. However, these overfitted image codecs are not fully optimized toward the rate-distortion objective: their network weights remain in full precision during training, and the associated quantization parameters are selected in a separate post-training stage. Furthermore, their synthesis operates at a single scale, which overlooks cross-scale redundancy. In this paper, we propose MIRC, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC. We further introduce a multi-scale representation with cross-stage parameter sharing, which improves coding efficiency at a small transmitted overhead. On the CLIC2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0). Moreover, MIRC offers a family of configurations spanning 1.2 to 2.9 kMAC per pixel, so the decoding budget can be selected to match the deployment target.

View source

Similar papers

Preprint Aug 2026

FLM: Frequency-Aware Language Models for Generative Image Compression

FLM is a frequency-aware language model that improves compression efficiency through frequency-domain probabilistic modeling while retaining deterministic reconstruction and is validated to be applicable to the lossless recompression task with competitive performance.

Jia-Run Chen, Ke-Jun Wu, Li Li et al. · 0 citations
Conference Open access Sep 2026

Choosing the Right Image Format for Web Performance

The exponential growth of visual content on the web has made image compression a critical discipline at the intersection of signal processing and perceptual psychology. Contemporary codecs, particularly AVIF and WebP, achieve remarkable compression efficiency not by discarding data arbitrarily, but by exploiting the st...

Shailesh Kadam · 0 citations
Preprint Sep 2026

Scalable Neural Video Representation Compression

The proposed S-NVRC spans a wide range of bitrate and decoding-complexity using a single encoding (training) and outperforms SHM 12.4 and the multi-layer VTM-20.0, by 43.7% and 5.6% in BD-rate on the UVG dataset, while also providing flexible complexity scalability.

Tian-Hao Peng, Ho-Man Kwan, Fan Zhang et al. · 0 citations
Preprint Sep 2026

Rate-Adaptive One-Step Diffusion Compression for AIGC Images

We describe our entry to the LoViF 2026 AIGC Image Compression Challenge, a benchmark for ultra-low-bitrate coding of AI-generated images under a strict global rate budget of 0.025 bits per pixel (BPP). Generated imagery poses a distinct challenge for compression: it frequently contains rendered typography, synthetic e...

Nitiz Khanal · 0 citations
Preprint Sep 2026

CASR: Content-Adaptive Neural Super-Resolution Post-Filter for Versatile Video Coding via Low-Rank Overfitting

The use of super-resolution as a post-processing step following a video codec allows videos to be encoded at reduced spatial resolution at the encoder side and to be reconstructed and upsampled to the original resolution at the decoder side. In this way, the required bitrate is reduced and the quality of the reconstruc...

Khoa Pham-Dinh, Francesco Cricri, María Santamaría et al. · 0 citations
#artificial intelligence Preprint Oct 2026

H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression

Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaus...

Or Ronai, Vladimir Kulikov, T. Michaeli · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.