当前位置: X-MOL 学术J. Visual Commun. Image Represent. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Superpixel alpha-expansion and normal adjustment for stereo matching
Journal of Visual Communication and Image Representation ( IF 2.6 ) Pub Date : 2021-07-22 , DOI: 10.1016/j.jvcir.2021.103238
Penglei Ji 1 , Jie Li 1 , Hanchao Li 1 , Xinguo Liu 1
Affiliation  

This paper presents a continuous stereo disparity estimation method based on superpixel segmentation and graph-cuts. We re-parameterize the disparity with a 3D tangent plane, and propose two algorithms to optimize the Markov Random Field (MRF) energy. The first algorithm, called superpixel α-expansion, is built on superpixel segmentation to localize the label proposal and the expansion scope. Three levels of superpixels with increasing granularity are generated for acceleration. The second algorithm, called normal adjustment, optimizes the 3D planes for the regions with low texture and/or illumination changes. The normal adjustment is performed along a depth-first similarity path of superpixels. We evaluate our method on the Middlebury 3.0 evaluation benchmark and the Eth3d benchmark. Experimental results show that our method achieves high accuracy on both evaluation benchmarks. (Middlebury 3.0 evaluation benchmark: http://vision.middlebury.edu/stereo/eval3/. Eth3d benchmark: https://www.eth3d.net/low_res_two_view.)



中文翻译:

立体匹配的超像素 alpha 扩展和法线调整

本文提出了一种基于超像素分割和图形切割的连续立体视差估计方法。我们使用 3D 切平面重新参数化视差,并提出了两种算法来优化马尔可夫随机场 (MRF) 能量。第一种算法,称为超像素α-expansion,建立在超像素分割的基础上,用于定位标签提议和扩展范围。为加速生成三级粒度增加的超像素。第二种算法称为法线调整,可优化纹理和/或光照变化低的区域的 3D 平面。沿着超像素的深度优先相似性路径执行正常调整。我们在 Middlebury 3.0 评估基准和 Eth3d 基准上评估我们的方法。实验结果表明,我们的方法在两个评估基准上都实现了高精度。(Middlebury 3.0 评估基准:http://vision.middlebury.edu/stereo/eval3/。Eth3d 基准:https://www.eth3d.net/low_res_two_view。)

更新日期:2021-08-01
down
wechat
bug