cd /news/computer-vision/comex-a-composition-grounded-benchma… · home topics computer-vision article
[ARTICLE · art-91455] src=arxiv.org ↗ pub= topic=computer-vision verified=true sentiment=· neutral

COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping

Researchers introduced COMEX, a benchmark with 33,161 quadruples of expanded images, crop boxes, composition categories, and explanations, to reformulate explainable aesthetic image cropping as a structured crop-composition-explanation problem. They proposed a two-stage SFT+GRPO framework that improves crop quality, composition prediction, and explanation faithfulness, benchmarking 15 large vision-language models and existing cropping methods on COMEX.

read1 min views1 publishedAug 11, 2026

arXiv:2608.07570v1 Announce Type: new Abstract: Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred. Existing crop-and-explain methods largely treat explanation as post-hoc text generation and overlook composition, a key aesthetic factor that links crop decisions with interpretable reasoning. In this paper, we reformulate explainable aesthetic image cropping as a structured crop-composition-explanation problem. To support this setting, we introduce COMEX, a new benchmark built through image expansion and an IO-reversal pipeline. COMEX contains 33,161 quadruples, each consisting of an expanded image, a crop box, a composition category, and a composition-grounded explanation, enabling joint learning of crop localization, composition understanding, and explanation generation. We further propose a two-stage SFT+GRPO framework, where supervised fine-tuning establishes the structured output protocol and basic cropping ability, and GRPO further improves crop quality, composition prediction, and explanation faithfulness. We benchmark 15 large vision-language models and existing cropping methods on COMEX, establishing a comprehensive testbed for composition-grounded explainable aesthetic cropping. Experiments on both COMEX and prior benchmarks demonstrate the effectiveness and transferability of our framework, with strong performance across evaluation metrics.

── more in #computer-vision 4 stories · sorted by recency
── more on @comex 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/comex-a-composition-…] indexed:0 read:1min 2026-08-11 ·