2D-to-3D Stereoscopic conversion: Depth estimation in monoscopic soccer videos

Ko, Jaeseung; Kim, Young Woo; Jung, Young-Ju; Kim, Changick

doi:10.5909/jbe.2008.13.4.427

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To tackle this issue many researchers have explored 2D-to-3D conversion techniques. However, previous methods are either semi-automatic [19,26] or cannot handle complex motions [12,21,13,10,11]. There has not been a 2D-to-3D conversion technique for soccer capable of handling complex motions with variety of scene structures, to the best of our knowledge.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, strong assumptions are often made on the depth distribution within a given scene. For example, Ko et al [12] classify shots into long or non-long, where long shots are assumed to have a large field view and a depth ramp is assigned to the whole image, and players are assigned a constant depth. Similarly Schnyder et al [21] detect players and assign constant depth to them.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Gradient-based 2D-to-3D Conversion for Soccer Videos

Calagari

Elgharib

Didyk

et al. 2015

Proceedings of the 23rd ACM International Conference on Multimedia

View full text Add to dashboard Cite

A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artifacts that are not acceptable to many viewers. We address this problem by showing how to construct a high-quality, domainspecific conversion method for soccer videos. We propose a novel, data-driven method that generates stereoscopic frames by transferring depth information from similar frames in a database of 3D stereoscopic videos. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. One of the key findings in this paper is showing that computer generated content in current sports computer games can be used to generate high-quality 3D video reference database for 2D-to-3D conversion methods. Once we retrieve similar 3D video frames, our technique transfers depth gradients to the target frame while respecting object boundaries. It then computes depth maps from the gradients, and generates the output stereoscopic video. We implement our method and validate it by conducting user-studies that evaluate depth perception and visual comfort of the converted 3D videos. We show that our method produces high-quality 3D videos that are almost indistinguishable from videos shot by stereo cameras. In addition, our method significantly outperforms the current state-of-the-art method. For example, up to 20% improvement in the perceived depth is achieved by our method, which translates to improving the mean opinion score from Good to Excellent.

show abstract