Photometric Stabilization for Fast‐forward Videos

Abstract

Videos captured by consumer cameras often exhibit temporal variations in color and tone that are caused by camera autoadjustments like white-balance and exposure. When such videos are sub-sampled to play fast-forward, as in the increasingly popular forms of timelapse and hyperlapse videos, these temporal variations are exacerbated and appear as visually disturbing high frequency flickering. Previous techniques to photometrically stabilize videos typically rely on computing dense correspondences between video frames, and use these correspondences to remove all color changes in the video sequences. However, this approach is limited in fast-forward videos that often have large content changes and also might exhibit changes in scene illumination that should be preserved. In this work, we propose a novel photometric stabilization algorithm for fast-forward videos that is robust to large content-variation across frames. We compute pairwise color and tone transformations between neighboring frames and smooth these pair-wise transformations while taking in account the possibility of scene/content variations. This allows us to eliminate high-frequency fluctuations, while still adapting to real variations in scene characteristics. We evaluate our technique on a new dataset consisting of controlled synthetic and real videos, and demonstrate that our techniques outperforms the state-of-the-art.

Deep Learning vs. Traditional Computer Vision

“…We will discuss later in this paper how many image transformation techniques can be used to improve your neural net training. Finally, there are many more challenging problems in CV such as: Robotics [21], augmented reality [22], automatic panorama stitching [23], virtual reality [24], 3D modelling [24], motion estimation [24], video stabilization [21], motion capture [24], video processing [21] and scene understanding [25] which cannot simply be easily implemented in a differentiable manner with deep learning but benefit from solutions using "traditional" techniques.…”

Integrating Traditional Machine Learning and Neural Networks for Image Processing

“…At the moment, traditional computer vision algorithms more suitable for simple tasks when computing resources or dataset limited. Application of machine learning algorithm are following: robotics [29], augmented reality [30], automatic panorama stitching [31], virtual reality [32], 3D modeling [32], motion estimation [32], video stabilization [29], motion capture [32], video processing [29] and scene understanding [33].…”