GRHCROJun 27, 2019

Optimizing for Aesthetically Pleasing Quadrotor Camera Motion

arXiv:1906.11686v137 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of creating visually appealing aerial videos for users like filmmakers and hobbyists, representing an incremental improvement over existing methods.

The paper tackled the problem of generating aesthetically pleasing quadrotor camera motion by first conducting a large-scale study to understand aesthetic perception, revealing the importance of smooth trajectories and expert timing control. They then proposed a joint optimization method for position and timing, which outperformed state-of-the-art in usability and preference, producing smoother results for novices and benefiting experts.

In this paper we first contribute a large scale online study (N=400) to better understand aesthetic perception of aerial video. The results indicate that it is paramount to optimize smoothness of trajectories across all keyframes. However, for experts timing control remains an essential tool. Satisfying this dual goal is technically challenging because it requires giving up desirable properties in the optimization formulation. Second, informed by this study we propose a method that optimizes positional and temporal reference fit jointly. This allows to generate globally smooth trajectories, while retaining user control over reference timings. The formulation is posed as a variable, infinite horizon, contour-following algorithm. Finally, a comparative lab study indicates that our optimization scheme outperforms the state-of-the-art in terms of perceived usability and preference of resulting videos. For novices our method produces smoother and better looking results and also experts benefit from generated timings.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes