# Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field

arXiv: https://arxiv.org/abs/2602.20363 · HTML: https://mlsanity.com/paper/2602.20363/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction](https://mlsanity.com/paper/2402.16174/) (2024)
- [Reliable and Efficient Image Cropping: A Grid Anchor based Approach](https://mlsanity.com/paper/1904.04441/) (2019)
- [Image Composition Assessment with Saliency-augmented Multi-pattern Pooling](https://mlsanity.com/paper/2104.03133/) (2021)
- [NeRF Director: Revisiting View Selection in Neural Volume Rendering](https://mlsanity.com/paper/2406.08839/) (2024)
- [UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images](https://mlsanity.com/paper/2506.09378/) (2025)
- [SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields](https://mlsanity.com/paper/2506.09565/) (2025)
- [Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition](https://mlsanity.com/paper/2309.12042/) (2023)
- [Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces](https://mlsanity.com/paper/2403.04508/) (2024)
- [AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning](https://mlsanity.com/paper/2109.09923/) (2021)
- [Towards Smart Point-and-Shoot Photography](https://mlsanity.com/paper/2505.03638/) (2025)
- [Camera View Adjustment Prediction for Improving Image Composition](https://mlsanity.com/paper/2104.07608/) (2021)
- [ViewActive: Active viewpoint optimization from a single image](https://mlsanity.com/paper/2409.09997/) (2024)
- [Photography Perspective Composition: Towards Aesthetic Perspective Recommendation](https://mlsanity.com/paper/2505.20655/) (2025)
- [3D View Optimization for Improving Image Aesthetics](https://mlsanity.com/paper/2405.16443/) (2024)

## Built on by (most cited first, 1 of 1)

- [PhotoFlow: Agentic 3D Virtual Photography Missions](https://mlsanity.com/paper/2605.23771/) (2026)

## Abstract (arXiv)

The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.