Prompt-Guided Prefiltering for VLM Image Compression

• URL: http://arxiv.org/abs/2604.00314v1
• Date: Tue, 31 Mar 2026 23:27:12 GMT
• Title: Prompt-Guided Prefiltering for VLM Image Compression
• Abstract summary: We propose a lightweight, plug-and-play, prompt-guided prefiltering module to identify image regions most relevant to text prompt.<n>Experiments on several VQA benchmarks show that our approach achieves a 25-50% average reduction while maintaining the same task accuracy.
• Score: 17.40790836107761
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid progress of large Vision-Language Models (VLMs) has enabled a wide range of applications, such as image understanding and Visual Question Answering (VQA). Query images are often uploaded to the cloud, where VLMs are typically hosted, hence efficient image compression becomes crucial. However, traditional human-centric codecs are suboptimal in this setting because they preserve many task-irrelevant details. Existing Image Coding for Machines (ICM) methods also fall short, as they assume a fixed set of downstream tasks and cannot adapt to prompt-driven VLMs with an open-ended variety of objectives. We propose a lightweight, plug-and-play, prompt-guided prefiltering module to identify image regions most relevant to the text prompt, and consequently to the downstream task. The module preserves important details while smoothing out less relevant areas to improve compression efficiency. It is codec-agnostic and can be applied before conventional and learned encoders. Experiments on several VQA benchmarks show that our approach achieves a 25-50% average bitrate reduction while maintaining the same task accuracy. Our source code is available at https://github.com/bardia-az/pgp-vlm-compression.

Related papers

• VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
  Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
  arXiv  Detail & Related papers  (2026-07-14T13:21:36Z)
• CoPE-VideoLM: Codec Primitives For Efficient Video Language Models [56.76440182038839]
  Video Language Models (VideoLMs) empower AI systems to understand temporal dynamics in videos.<n>Current methods use sampling which can miss both macro-level events and micro-level details due to the sparse temporal coverage.<n>We propose to leverage video primitives which encode video redundancy and sparsity without requiring expensive full-image encoding for most frames.
  arXiv  Detail & Related papers  (2026-02-13T18:57:31Z)
• Benchmarking and Enhancing VLM for Compressed Image Understanding [52.98037879935058]
  Vision-Language Models (VLMs) predominantly digest and understand high-bitrate compressed images.<n>Their ability to interpret low-bitrate compressed images has yet to be explored by far.<n>We introduce the first comprehensive benchmark to evaluate the ability of VLM against compressed images.
  arXiv  Detail & Related papers  (2025-12-24T02:59:01Z)
• RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression [68.31184784672227]
  In modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems performing tasks.<n>It is therefore useful to optimize the encoder for a downstream task instead of for image quality.<n>Here, we address this challenge by controlling the Quantization Parameters (QPs) at the macro-block level to optimize the downstream task.
  arXiv  Detail & Related papers  (2025-01-21T15:36:08Z)
• 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)
• 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)
• You Can Mask More For Extremely Low-Bitrate Image Compression [80.7692466922499]
  Learned image compression (LIC) methods have experienced significant progress during recent years. LIC methods fail to explicitly explore the image structure and texture components crucial for image compression. We present DA-Mask that samples visible patches based on the structure and texture of original images. We propose a simple yet effective masked compression model (MCM), the first framework that unifies LIC and LIC end-to-end for extremely low-bitrate compression.
  arXiv  Detail & Related papers  (2023-06-27T15:36:22Z)
• Preprocessing Enhanced Image Compression for Machine Vision [14.895698385236937]
  We propose a preprocessing enhanced image compression method for machine vision tasks. Our framework is built upon the traditional non-differential codecs. Experimental results show our method achieves a better tradeoff between the coding and the performance of the downstream machine vision tasks by saving about 20%.
  arXiv  Detail & Related papers  (2022-06-12T03:36:38Z)
• Microdosing: Knowledge Distillation for GAN based Compression [18.140328230701233]
  We show how to leverage knowledge distillation to obtain equally capable image decoders at a fraction of the original number of parameters. This allows us to reduce the model size by a factor of 20 and to achieve 50% reduction in decoding time.
  arXiv  Detail & Related papers  (2022-01-07T14:27:16Z)
• How to Exploit the Transferability of Learned Image Compression to Conventional Codecs [25.622863999901874]
  We show how learned image coding can be used as a surrogate to optimize an image for encoding. Our approach can remodel a conventional image to adjust for the MS-SSIM distortion with over 20% rate improvement without any decoding overhead.
  arXiv  Detail & Related papers  (2020-12-03T12:34:51Z)

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.