fxguidetv #138: CVMP Conference

Coverage from CVMP, a conference that brings together image science researchers and creatives in production and post. Excerpts from papers on Automatic Object Segmentation from Calibrated Images and HD Stereoscopic Free Viewpoint Video.

---

Making of “Who Cares?” – HD Stereoscopic Free Viewpoint Video

Christian Lipski, Felix Klose, Kai Ruhl, Marcus Magnor (TU Braunschweig)

Abstract
We present a detailed blueprint of our stereoscopic free-viewpoint video system.Using unsynchronized footage as input, we can render virtual camera paths in the post-production stage. The movement of the virtual camera also extends to the temporal domain, so that slow-motion and freeze-and-rotate shots are possible. As a proof-of-concept, a full length stereoscopic HD music video has been produced using our approach.

Download a pdf of the technical paper.

Here’s the completed video, “Who Cares” by Symbiz

 

Automatic Object Segmentation from Calibrated Images

Neill Campbell (University of Cambridge), George Vogiatzis (Aston University), Carlos Hernandez-Esteban (Google), Roberto Cipolla (University of Cambridge)

Abstract
This paper concerns the automatic recovery of binary object/background segmentations of a central object in a set of calibrated images. The resulting segmentations may be used to recover the shape of the object, particularly useful in scenes where MVS methods are unable to recover the full surface, e.g. textureless objects (Plant dataset). The results are also useful as an input to MVS algorithms, either to increase accuracy or decrease computation time.

Our approach combines multiple cues (object/background appearance models, epipolar constraints and weak stereo correspondence) into a single energy-based framework that may be solved efficiently. We achieve superior performance to previous publications as well as MVS methods when observing a textureless object.

Download a pdf of the technical paper.