Oriel — AI & technology worth noticing, every day.

PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments

Paper · https://arxiv.org/abs/2611.02897

Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers no such guarantee: the viewing direction in a scene has to be discovered before anything can be framed. We present PhotoGuider, a measure-then-frame method that answers both questions with compact learned scorers over one shared set of composition-aware features. The designed features are extracted using foundation and task-specific vision models and structured into four photographic tokens: Subject, Composition, Aesthetics, and Integrity. Our MLLM explainer is fine-tuned to generate composition-related explanations conditioned on images and measured token assessments. To our knowledge, PhotoGuider is the first method to combine explicit composition-based direction selection in 360^{circ} panoramas with refined framing, camera-parameter output for native re-rendering, and measurement-conditioned explanations. On two standard 2D cropping benchmarks, PhotoGuider achieves the highest average mIoU performance against ground-truth crops. In a blind ranking study, 120 participants ranked three cropping methods over 100 panoramic scenes from the public Poly Haven HDRI library, placing our framings first in 53.2% of cases, against 27.3% and 19.5% for two strong alternatives. Project page: https://ntuneillee.github.io/research/photoguider/

First seen by Oriel on .

AI summary

PhotoGuider combines composition-aware direction selection and framing for 360° panoramas, reporting top average mIoU on two 2D cropping benchmarks and first place in 53.2% of panoramic-scene rankings.

  • It uses compact learned scorers over shared features extracted with foundation and task-specific vision models.
  • Four photographic tokens measure Subject, Composition, Aesthetics, and Integrity; an MLLM generates explanations conditioned on images and token assessments.
  • The method outputs camera parameters for native re-rendering and refines framing after selecting a viewing direction.
  • In a blind study of 120 participants ranking three methods across 100 Poly Haven HDRI scenes, PhotoGuider framings ranked first 53.2% of the time, versus 27.3% and 19.5% for alternatives.

#image cropping #360 panoramas #computer vision #multimodal llms

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 38, latest observation ; +10 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 1, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2611.02897https://arxiv.org/abs/2611.02897 Read discussion