Depth Extraction from Video Using Non-parametric Sampling
This addresses the problem of depth estimation for 3D visualization in videos, particularly in challenging cases like non-translating cameras and dynamic scenes, though it appears incremental as it builds on existing sampling methods.
The paper tackles depth map generation from videos using non-parametric sampling, achieving state-of-the-art performance on benchmark databases and enabling automatic conversion of monoscopic videos to stereo for 3D visualization.
We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling. We demonstrate our technique in cases where past methods fail (non-translating cameras and dynamic scenes). Our technique is applicable to single images as well as videos. For videos, we use local motion cues to improve the inferred depth maps, while optical flow is used to ensure temporal depth consistency. For training and evaluation, we use a Kinect-based system to collect a large dataset containing stereoscopic videos with known depths. We show that our depth estimation technique outperforms the state-of-the-art on benchmark databases. Our technique can be used to automatically convert a monoscopic video into stereo for 3D visualization, and we demonstrate this through a variety of visually pleasing results for indoor and outdoor scenes, including results from the feature film Charade.