Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
This addresses the challenge for photographers and content creators by providing efficient viewpoint suggestions without dense captures or costly reinforcement learning, though it is incremental as it builds on existing 2D aesthetic models and 3D techniques.
The paper tackles the problem of suggesting aesthetically pleasing camera viewpoints by introducing a 3D aesthetic field that enables geometry-grounded reasoning with sparse captures, resulting in viewpoints with superior framing and composition compared to existing methods.
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.