HuggingFace Daily Papers·· 2 天前
PhotoGuider：面向 360° 全景的构图感知裁剪与可解释取景
PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments
AI 导读
PhotoGuider 提出“先测量后取景”方法，用共享构图感知特征上的轻量学习评分器，同时完成 360° 全景的取景方向选择与精细裁剪。该方法将特征组织为 Subject、Composition、Aesthetics、Integrity 四类摄影 token，并由微调的 MLLM 解释器生成构图相关解释，同时输出相机参数以支持原生重渲染。
正文 · 原文
Abstract: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: this https URL
| Comments: | 25 pages, 8 figures. Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2611.02897 [cs.CV] |
| (or arXiv:2611.02897v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02897 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: YuanKang Lee [view email]
[v1]
Mon, 2 Nov 2026 10:31:22 UTC (11,406 KB)
来源：HuggingFace Daily Papers · arxiv.org