Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent

• URL: http://arxiv.org/abs/2508.15243v1
• Date: Thu, 21 Aug 2025 05:09:30 GMT
• Title: Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
• Authors: Yixin Gao, Xin Li, Xiaohan Pan, Runsen Feng, Bingchen Li, Yunpeng Qi, Yiting Lu, Zhengxue Cheng, Zhibo Chen, Jörn Ostermann,
• Abstract summary: We present Comp-X, the first intelligently interactive image compression paradigm empowered by the impressive reasoning capability of large language model (LLM) agent.<n>Our proposed Comp-X can understand the coding requests efficiently and achieve impressive textual interaction capability.
• Score: 22.508271684976073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Comp-X, the first intelligently interactive image compression paradigm empowered by the impressive reasoning capability of large language model (LLM) agent. Notably, commonly used image codecs usually suffer from limited coding modes and rely on manual mode selection by engineers, making them unfriendly for unprofessional users. To overcome this, we advance the evolution of image coding paradigm by introducing three key innovations: (i) multi-functional coding framework, which unifies different coding modes of various objective/requirements, including human-machine perception, variable coding, and spatial bit allocation, into one framework. (ii) interactive coding agent, where we propose an augmented in-context learning method with coding expert feedback to teach the LLM agent how to understand the coding request, mode selection, and the use of the coding tools. (iii) IIC-bench, the first dedicated benchmark comprising diverse user requests and the corresponding annotations from coding experts, which is systematically designed for intelligently interactive image compression evaluation. Extensive experimental results demonstrate that our proposed Comp-X can understand the coding requests efficiently and achieve impressive textual interaction capability. Meanwhile, it can maintain comparable compression performance even with a single coding framework, providing a promising avenue for artificial general intelligence (AGI) in image compression.

Related papers

• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution [71.69364653858447]
  Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs.<n>We propose Visual Consistency Learning (ViCO), a novel training algorithm that enables the model to represent images of varying complexities using different numbers of vision tokens.<n> Experimental results demonstrate that our method can reduce the number of vision tokens by up to 50% while maintaining the model's perception, reasoning, and OCR capabilities.
  arXiv  Detail & Related papers  (2025-10-14T17:58:10Z)
• Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions [81.33113485830711]
  We introduce a vision-free, single-encoder retrieval pipeline for vision-language models.<n>We migrate to a text-to-text paradigm with the assistance of VLLM-generated structured image descriptions.<n>Our approach achieves state-of-the-art zero-shot performance on multiple retrieval and compositionality benchmarks.
  arXiv  Detail & Related papers  (2025-09-23T16:22:27Z)
• METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models [92.37117312251755]
  We propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR)<n>For multi-vision encoding, we discard redundant tokens within each encoder via a rank guided collaborative token assignment strategy.<n>For multi-vision fusion, we combine the visual features from different encoders while reducing cross-encoder redundancy with cooperative pruning.
  arXiv  Detail & Related papers  (2025-07-28T13:50:53Z)
• Explicit Residual-Based Scalable Image Coding for Humans and Machines [0.0]
  scalable image compression methods serve both machine and human vision.<n>In this paper, we enhance the coding efficiency and interpretability of ICMH framework by integrating an explicit residual compression mechanism.<n>We propose two complementary methods: Feature Residual-based Residual-based Coding (FR-ICMH) and Pixel Residual-based Residual-based Coding (PR-ICMH)
  arXiv  Detail & Related papers  (2025-06-24T04:01:53Z)
• UniMIC: Towards Universal Multi-modality Perceptual Image Compression [21.370591256689885]
  We present UniMIC, a universal multi-modality image compression framework.<n>UniMIC aims to unify the rate-distortion-perception (RDP) optimization for multiple image codecs.
  arXiv  Detail & Related papers  (2024-12-06T10:08:55Z)
• Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs [47.7670923159071]
  We present a new image compression paradigm to achieve intelligently coding for machine'' by cleverly leveraging the common sense of Large Multimodal Models (LMMs) We dub our method textitSDComp'' for textitSemantically textitDisentangled textitCompression'', and compare it with state-of-the-art codecs on a wide variety of different vision tasks.
  arXiv  Detail & Related papers  (2024-08-16T07:23:18Z)
• Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation [54.23510028456082]
  We propose a Triple-view Knowledge Distillation framework, termed TriKD, for semi-supervised semantic segmentation. The framework includes the triple-view encoder and the dual-frequency decoder.
  arXiv  Detail & Related papers  (2023-09-22T01:02:21Z)
• Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts [27.119835579428816]
  Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. Inspired by recent advances in transferring large-scale pre-trained models to downstream tasks via prompting, we explore a new ICM framework, Prompt-ICM. Our method is composed of two core designs: a) compression prompts, which are implemented as importance maps predicted by an information selector, and used to achieve different content-weighted bit allocations during compression according to different downstream tasks.
  arXiv  Detail & Related papers  (2023-05-04T06:21:10Z)
• Generalized Decoding for Pixel, Image, and Language [197.85760901840177]
  We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decoder is the first work that provides a unified way to support all types of image segmentation and a variety of vision-language (VL) tasks.
  arXiv  Detail & Related papers  (2022-12-21T18:58:41Z)
• ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding [9.908820641439368]
  We propose an efficient model, ELIC, to achieve state-of-the-art speed and compression ability. With superior performance, the proposed model also supports extremely fast preview decoding and progressive decoding.
  arXiv  Detail & Related papers  (2022-03-21T11:19:50Z)
• Neural Data-Dependent Transform for Learned Image Compression [72.86505042102155]
  We build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism.
  arXiv  Detail & Related papers  (2022-03-09T14:56:48Z)
• Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics [127.65410486227007]
  Video coding, which targets to compress and reconstruct the whole frame, and feature compression, which only preserves and transmits the most critical information, stand at two ends of the scale. Recent endeavors in imminent trends of video compression, e.g. deep learning based coding tools and end-to-end image/video coding, and MPEG-7 compact feature descriptor standards, promote the sustainable and fast development in their own directions. In this paper, thanks to booming AI technology, e.g. prediction and generation models, we carry out exploration in the new area, Video Coding for Machines (VCM), arising from the emerging MPEG
  arXiv  Detail & Related papers  (2020-01-10T17:24:13Z)

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.