Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks

• URL: http://arxiv.org/abs/2607.07189v1
• Date: Wed, 08 Jul 2026 09:23:56 GMT
• Title: Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks
• Abstract summary: Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks.<n>It remains unclear whether they can handle the physics and inverse problems that underlie computational imaging.<n>We present ImagingBench, a benchmark of 20 computational imaging tasks spanning five categories.
• Score: 3.146480929844211
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks, but it remains unclear whether they can handle the physics and inverse problems that underlie computational imaging. We present ImagingBench, a benchmark of 20 computational imaging tasks spanning five categories: ray and wave optics, image signal processing, inverse reconstruction, computational sensing, and calibration. ImagingBench evaluates three complementary settings: Expert, fixed expert-guided inverse reconstruction; Planner, planner-guided inverse reconstruction; and Forward, forward-system simulation for consistency checking. We benchmark leading proprietary and open-source image-centric multimodal systems, including Gemini, GPT, and Qwen, and compare them with representative task-specific non-agentic baselines. Across tasks, agentic models remain consistently weaker than specialized methods, especially on computational sensing problems such as lensless imaging, event-based reconstruction, time-of-flight imaging, and holography. Planner guidance provides only modest and inconsistent gains over the fixed-prompt Expert baseline. Although the models often generate visually plausible outputs, their reference-based fidelity remains poor, revealing a substantial gap between semantic visual competence and physically grounded imaging performance. ImagingBench provides a unified testbed for measuring this gap and tracking progress in agentic AI for computational imaging.

Related papers

• Can Vision-Language Models Reason about AI Edits in Images? [78.04125956307838]
  Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities.<n>We propose a GRPO-based training framework that utilizes simple accuracy and format rewards.<n>Our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors.
  arXiv  Detail & Related papers  (2026-07-30T16:23:40Z)
• Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging [9.890461939894694]
  We introduce Imaging-101, a benchmark of 57 expert-verified computational imaging tasks spanning six scientific domains.<n>Three evaluation tracks (planning, function-level unit tests, and end-to-end reconstruction) probe distinct agent capabilities across the full pipeline.
  arXiv  Detail & Related papers  (2026-07-12T14:42:57Z)
• GenShield: Unified Detection and Artifact Correction for AI-Generated Images [65.11434977803509]
  GenShield is a framework that performs AIGI detection and artifact correction in a closed loop from diagnosis to restoration.<n>A high-quality dataset with large-scale artifact-restored'' pairs is constructed alongside a unified evaluation pipeline.
  arXiv  Detail & Related papers  (2026-05-15T16:06:20Z)
• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing [56.60465182650588]
  We introduce three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning.<n>We propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment.<n>We find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models.
  arXiv  Detail & Related papers  (2026-02-02T09:24:45Z)
• More Images, More Problems? A Controlled Analysis of VLM Failure Modes [80.64323947730905]
  Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored.<n>We introduce MIMIC, a new benchmark designed to rigorously evaluate the multi-image capabilities of LVLMs.
  arXiv  Detail & Related papers  (2026-01-12T18:45:13Z)
• Semantic-Aware Reconstruction Error for Detecting AI-Generated Images [22.83053631078616]
  We propose a novel representation, namely Semantic-Aware Reconstruction Error (SARE), that measures the semantic difference between an image and its caption-guided reconstruction.<n>SARE provides a robust and discriminative feature for detecting fake images across diverse generative models.<n>We also introduce a fusion module that integrates SARE into the backbone detector via a cross-attention mechanism.
  arXiv  Detail & Related papers  (2025-08-13T04:37:36Z)
• RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
  RIGID is a training-free and model-agnostic method for robust AI-generated image detection. RIGID significantly outperforms existing trainingbased and training-free detectors.
  arXiv  Detail & Related papers  (2024-05-30T14:49:54Z)
• Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction [13.277067849874756]
  We study how DIP recovers information from undersampled imaging measurements. We introduce a self-driven reconstruction process that concurrently optimize both the network weights and the input. Our method incorporates a novel denoiser regularization term which enables robust and stable joint estimation of both the network input and reconstructed image.
  arXiv  Detail & Related papers  (2024-02-06T15:52:23Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)

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.