3D Ken Burns Effect from a Single Image

TL;DR

This paper presents an automatic framework to generate 3D Ken Burns effects from a single image by estimating depth, synthesizing views, and inpainting disocclusions, enabling realistic animations with minimal user effort.

Contribution

The authors introduce a novel method that synthesizes 3D Ken Burns effects from a single image using a semantic-aware depth prediction and inpainting, reducing manual effort and input requirements.

Findings

Produces realistic 3D Ken Burns animations from a single image.

Outperforms existing methods in depth accuracy and visual coherence.

Enables user-controlled camera paths with minimal manual intervention.

Abstract

The Ken Burns effect allows animating still images with a virtual camera scan and zoom. Adding parallax, which results in the 3D Ken Burns effect, enables significantly more compelling results. Creating such effects manually is time-consuming and demands sophisticated editing skills. Existing automatic methods, however, require multiple input images from varying viewpoints. In this paper, we introduce a framework that synthesizes the 3D Ken Burns effect from a single image, supporting both a fully automatic mode and an interactive mode with the user controlling the camera. Our framework first leverages a depth prediction pipeline, which estimates scene depth that is suitable for view synthesis tasks. To address the limitations of existing depth estimation methods such as geometric distortions, semantic distortions, and inaccurate depth boundaries, we develop a semantic-aware neural network for depth prediction, couple its estimate with a segmentation-based depth adjustment process, and employ a refinement neural network that facilitates accurate depth predictions at object boundaries. According to this depth estimate, our framework then maps the input image to a point cloud and synthesizes the resulting video frames by rendering the point cloud from the corresponding camera positions. To address disocclusions while maintaining geometrically and temporally coherent synthesis results, we utilize context-aware color- and depth-inpainting to fill in the missing information in the extreme views of the camera path, thus extending the scene geometry of the point cloud. Experiments with a wide variety of image content show that our method enables realistic synthesis results. Our study demonstrates that our system allows users to achieve better results while requiring little effort compared to existing solutions for the 3D Ken Burns effect creation.