Abstract
Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines. However, building a correct reconstruction pipeline demands deep domain expertise and remains laborious even for domain scientists. We introduce Imaging-101, a benchmark of 57 expert-verified computational imaging tasks spanning six scientific domains, each grounded in a peer-reviewed paper and canonicalized into a standardized four-stage pipeline: preprocessing, forward physics modeling, inverse solver, and visualization.
Evaluation Tracks
Three evaluation tracks (planning, function-level unit tests, and end-to-end reconstruction) probe distinct agent capabilities across the full pipeline. Evaluating seven frontier LLMs uncovers systematic challenges in applying coding agents to computational imaging that go beyond those exposed by general coding benchmarks, spanning algorithm selection, physical convention handling, and pipeline integration.
These findings highlight concrete capability gaps and point toward skill-augmented, domain-specialized agents as a practical path to reliable computational imaging assistance.
Blogger's Review: This study provides a crucial benchmark for LLM applications in computational imaging, emphasizing the limitations of current technologies and promoting the development of domain-specific tools. Such approaches can enhance the efficiency of scientific research and foster interdisciplinary collaboration and innovation.