Paper Detail
Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu
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/
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{lee2026photoguider,
title = {PhotoGuider: Composition-Aware Cropping and 360\textasciicircum{}\{circ\} View Framing with Explainable Photographic Assessments},
author = {Yuan-Kang Lee and Kuan-Lin Chen and Chia-Che Chang and Yu-Lun Liu},
year = {2026},
abstract = {Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360\textasciicircum{}\{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 },
url = {https://huggingface.co/papers/2611.02897},
keywords = {MLLM, photographic tokens, composition-aware features, 360° panoramas, mIoU, camera-parameter output, foundation vision models, code available, huggingface daily},
eprint = {2611.02897},
archiveprefix = {arXiv},
}
{}