TY - GEN
T1 - High-quality real-time stereo using adaptive cost aggregation and dynamic programming
AU - Wang, Liang
AU - Liao, Miao
AU - Gong, Minglun
AU - Yang, Ruigang
AU - Nister, David
PY - 2006
Y1 - 2006
N2 - We present a stereo algorithm that achieves high quality results while maintaining real-time performance. The key idea is simple: we introduce an adaptive aggregation step in a dynamic-programming (DP) stereo framework. The per-pixel matching cost is aggregated in the vertical direction only. Compared to traditional DP, our approach reduces the typical "streaking" artifacts without the penalty of blurry object boundaries. Evaluation using the benchmark Middlebury stereo database shows that our approach is among the best (rankedfirst in the new evaluation system) for DP-based approaches. The performance gain mainly comes from a computationally expensive weighting scheme based on color and distance proximity. We utilize the vector processing capability and parallelism in commodity graphics hardware to speed up this process over two orders of magnitude. Over 50 million disparity evaluations per second (MDE/s)1 are achieved in our current implementation.
AB - We present a stereo algorithm that achieves high quality results while maintaining real-time performance. The key idea is simple: we introduce an adaptive aggregation step in a dynamic-programming (DP) stereo framework. The per-pixel matching cost is aggregated in the vertical direction only. Compared to traditional DP, our approach reduces the typical "streaking" artifacts without the penalty of blurry object boundaries. Evaluation using the benchmark Middlebury stereo database shows that our approach is among the best (rankedfirst in the new evaluation system) for DP-based approaches. The performance gain mainly comes from a computationally expensive weighting scheme based on color and distance proximity. We utilize the vector processing capability and parallelism in commodity graphics hardware to speed up this process over two orders of magnitude. Over 50 million disparity evaluations per second (MDE/s)1 are achieved in our current implementation.
UR - http://www.scopus.com/inward/record.url?scp=47249124504&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47249124504&partnerID=8YFLogxK
U2 - 10.1109/3DPVT.2006.75
DO - 10.1109/3DPVT.2006.75
M3 - Conference contribution
AN - SCOPUS:47249124504
SN - 0769528252
SN - 9780769528250
T3 - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
SP - 798
EP - 805
BT - Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
T2 - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Y2 - 14 June 2006 through 16 June 2006
ER -