Multi-scale Image Representation Compression

• URL: http://arxiv.org/abs/2609.04274v1
• Date: Wed, 02 Sep 2026 21:44:26 GMT
• Title: Multi-scale Image Representation Compression
• Abstract summary: MIRC is an overfitted image in which every coded component is quantized and entropy coded under a single rate-distortion objective.<n>On the CLIC 2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0).<n>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.
• Score: 21.36894041974722
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding [74.2282307661978]
  Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years.<n>In this work, we propose a feedforward INR image coding architecture, Practical INR Image Codec (PIC), that computes all the necessary information for INR network in a single forward pass.
  arXiv  Detail & Related papers  (2026-09-08T16:52:00Z)
• Scalable Neural Video Representation Compression [21.36894041974722]
  Implicit neural representation (INR) based codecs achieve compression by overfitting a compact neural network to an individual video.<n>This paper proposes S-NVRC, a scalable INR-based video that jointly supports fine-grained and decoding complexity from a single embedded bitstream.
  arXiv  Detail & Related papers  (2026-09-02T21:25:47Z)
• ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization [59.481950697968706]
  We propose Progressive Generative Image Compression (ProGIC), a compact built on residual vector quantization (RVQ)<n>In RVQ, a sequence of vector quantizers encodes the residuals stage by stage, each with its own codebook.<n>We pair this with a lightweight backbone based on depthwise-separable convolutions and small attention blocks, enabling practical deployment on both GPU and CPU-only devices.
  arXiv  Detail & Related papers  (2026-03-03T11:47:05Z)
• Ultra-lightweight Neural Video Representation Compression [18.390031994984096]
  We propose NVRC-Lite, which incorporates two key changes to neural video representation.<n>Firstly, we integrated multi-scale feature grids into our lightweight neural representation.<n> Secondly, we address the issue that existing INRs typically leverage autoregressive models for entropy coding.<n>Our experimental results demonstrate that NVRC-Lite outperforms C3, one of the best lightweight INR-based video codecs.
  arXiv  Detail & Related papers  (2025-12-03T17:56:44Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• CMC-Bench: Towards a New Paradigm of Visual Signal Compression [85.1839779884282]
  We introduce CMC-Bench, a benchmark of the cooperative performance of Image-to-Text (I2T) and Text-to-Image (T2I) models for image compression. At ultra-lows, this paper proves that the combination of some I2T and T2I models has surpassed the most advanced visual signal protocols.
  arXiv  Detail & Related papers  (2024-06-13T17:41:37Z)
• MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model [78.4051835615796]
  This paper proposes a method called Multimodal Image Semantic Compression. It consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. It can achieve optimal consistency and perception results while saving perceptual 50%, which has strong potential applications in the next generation of storage and communication.
  arXiv  Detail & Related papers  (2024-02-26T17:11:11Z)
• ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression [18.05997169440533]
  We propose ConvNeXt-ChARM, an efficient ConvNeXt-based transform coding framework, paired with a compute-efficient channel-wise auto-regressive auto-regressive. We show that ConvNeXt-ChARM brings consistent and significant BD-rate (PSNR) reductions estimated on average to 5.24% and 1.22% over the versatile video coding (VVC) reference encoder (VTM-18.0) and the state-of-the-art learned image compression method SwinT-ChARM.
  arXiv  Detail & Related papers  (2023-07-12T11:45:54Z)
• End-to-End Learnable Multi-Scale Feature Compression for VCM [8.037759667748768]
  We propose a novel multi-scale feature compression method that enables the end-to-end optimization on the extracted features and the design of lightweight encoders. Our model outperforms previous approaches by at least 52% BD-rate reduction and has $times5$ to $times27$ times less encoding time for object detection.
  arXiv  Detail & Related papers  (2023-06-29T04:05:13Z)
• Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder [73.48927855855219]
  We propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends. Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics.
  arXiv  Detail & Related papers  (2022-01-27T20:20:03Z)
• Slimmable Compressive Autoencoders for Practical Neural Image Compression [20.715312224456138]
  We propose slimmable compressive autoencoders (SlimCAEs) for practical image compression. SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency.
  arXiv  Detail & Related papers  (2021-03-29T16:12:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.