Research map / 3D vision / Gaussian splatting
Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
Sheyang Tang, Armin Shafiee Sarvestani, Jialu Xu, Xiaoyu Xu, Zhou Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| distill aesthetic features into 3D Gaussians instead of scoring rendered RGB (ablation) | Feedforward 3DGS aesthetic field · DL3DV 2 views | PLCC: 0.326 -> 0.509 | Improved |
| distill aesthetic features instead of RGB scoring (ablation) | Viewpoint suggestion · RE10k 2 views | VEN: 1.48 -> 1.89 | Improved |
| use distilled aesthetic field for gradient ascent instead of RGB scoring (ablation) | Viewpoint refinement · RE10k | Delta VEN: 0.20 -> 0.46 | Improved |
| add view-conditioning on camera poses (ablation) | Aesthetic field · RE10k 4 views | PLCC: 0.732 -> 0.796 | Improved |
| add view-conditioning on camera poses (ablation) | Aesthetic field · DL3DV 4 views | PLCC: 0.658 -> 0.700 | Improved |
| increase candidates K from 1 to 2 (ablation) | Coarse sampling · RE10k | VEN: 1.96 -> 2.03 | Improved |
| increase candidates K from 2 to 3 (ablation) | Coarse sampling · RE10k | VEN: 2.03 -> 2.05 | No clear effect |
| increase refinement steps from 25 to 30 (ablation) | Gradient refinement · RE10k | Delta VEN: 0.46 -> 0.49 | No clear effect |
| increase input views from 2 to 6 with distilled field | Viewpoint suggestion · DL3DV | VEN: 2.56 -> 2.91 | Improved |
| use ours versus rotation single-view approximation with more views | Viewpoint suggestion · DL3DV 6 views | VEN: 2.85 -> 2.91 | No clear effect |
Closest papers by meaning
- Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization (ICLR 2026 · similarity 0.88)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.86)
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms (NeurIPS 2024 · similarity 0.86)
- Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping (CVPR 2026 · similarity 0.86)
- Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization (CVPR 2025 · similarity 0.85)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
