arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.15325cs.CVcs.AIcs.LG
收藏

SE-MD:一种用于从2D图像生成点云的单编码器多解码器深度网络

SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images

University of Kashmir(克什米尔大学);South Valley University(南谷大学)

Abdul Mueed Hafiz, Rouf Ul Alam Bhat, Shabir Ahmad Parah, M. Hassaballah

摘要:

从单个2D RGB图像生成3D模型是一个具有挑战性的和积极研究的计算机视觉任务。已经提出了使用传统网络架构的各种技术。然而,研究工作的主体是有限的,并且存在各种问题,例如使用低效的3D表示格式,弱3D模型生成骨干,无法生成密集点云,依赖于生成密集点云的后处理,以及依赖于RGB图像中的轮廓。本文提出了一种新的2D RGB图像点云转换技术,它改善了该领域的最新技术水平,由于其高效,鲁棒和简单的模型,通过使用网络架构中的并行化概念。它不仅使用了点云的高效和丰富的3D表示,而且还使用了一个新颖的和强大的点云生成骨干,以解决普遍存在的问题。这涉及使用单编码器多解码器深度网络架构,其中每个解码器生成某些固定视点。然后融合所有视点以生成密集的点云。进行了各种实验的技术和它的性能与其他国家的最先进的技术和令人印象深刻的增益的性能进行了比较。代码可在https://github.com/mueedhafiz1982/上获得

英文摘要:

3D model generation from single 2D RGB images is a challenging and actively researched computer vision task. Various techniques using conventional network architectures have been proposed for the same. However, the body of research work is limited and there are various issues like using inefficient 3D representation formats, weak 3D model generation backbones, inability to generate dense point clouds, dependence of post-processing for generation of dense point clouds, and dependence on silhouettes in RGB images. In this paper, a novel 2D RGB image to point cloud conversion technique is proposed, which improves the state of art in the field due to its efficient, robust and simple model by using the concept of parallelization in network architecture. It not only uses the efficient and rich 3D representation of point clouds, but also uses a novel and robust point cloud generation backbone in order to address the prevalent issues. This involves using a single-encoder multiple-decoder deep network architecture wherein each decoder generates certain fixed viewpoints. This is followed by fusing all the viewpoints to generate a dense point cloud. Various experiments are conducted on the technique and its performance is compared with those of other state of the art techniques and impressive gains in performance are demonstrated. Code is available at https://github.com/mueedhafiz1982/

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑