PhotoGuider: Composition-Aware Cropping and 360 View Framing with Explainable Photographic Assessments
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-04
Project page: https://ntuneillee.github.io/research/photoguider/1
Terminology
Sources
- Qwen2.5-VL Technical Report
- NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
- CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
- Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping
- Creatism: A deep-learning photographer capable of creating professional work
- CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography
- AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception
- Before the Shutter: Aesthetic and Actionable Portrait Photography Planning in 3D Scenes
- ShutterMuse: Capture-Time Photography Guidance with MLLMs
- From Concepts to Judgments: Interpretable Image Aesthetic Assessment
- Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising
- InterpretML: A Unified Framework for Machine Learning Interpretability
- Camera View Adjustment Prediction for Improving Image Composition
- Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
- COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping
- Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
- Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs