실안개를 이용한 단일 영상으로부터의 깊이정보 획득 및 뷰 생성 알고리듬

Depth estimation and View Synthesis using Haze Information

  • 소용석 (서울대학교 전기공학부 신호처리연구실) ;
  • 현대영 (서울대학교 전기공학부 신호처리연구실) ;
  • 이상욱 (서울대학교 전기공학부 신호처리연구실)
  • Soh, Yong-Seok (Signal Processing Lab., School of Electrical Engineering, Seoul National University) ;
  • Hyun, Dae-Young (Signal Processing Lab., School of Electrical Engineering, Seoul National University) ;
  • Lee, Sang-Uk (Signal Processing Lab., School of Electrical Engineering, Seoul National University)
  • 발행 : 2010.07.08

초록

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

키워드