亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Normal Assisted Pixel-Visibility Learning With Cost Aggregation for Multiview Stereo

计算机科学 人工智能 计算机视觉 深度图 能见度 像素 立体视觉 图像(数学) 物理 光学
作者
Wei Tong,Xiaorong Guan,Jian Kang,Zhao-Hui Sun,Rob Law,Pedram Ghamisi,Edmond Q. Wu
出处
期刊:IEEE Transactions on Intelligent Transportation Systems [Institute of Electrical and Electronics Engineers]
卷期号:23 (12): 24686-24697 被引量:8
标识
DOI:10.1109/tits.2022.3193421
摘要

Multiple-View Stereo (MVS) aims to reconstruct the dense 3D representations of scenes. MVS has potential applications in the fields of autonomous driving (unstructured environment construction) and robotic navigation (visual-inertial navigation). To mitigate the error of depth estimation in low-textured or occluded regions, this work proposes a two-stage multi-view stereo network for fast and accurate depth estimation. The improvements of this work over the state of the art are as follows: 1) Sparse costs are constructed to jointly predict the initial depth map and surface normal by cost regularization, which proves that the surface normals can be estimated in this way with low memory consumption. 2) A new edge refinement block is developed to refine the coarse surface normal to obtain a fine-grained surface normal map. 3) Instead of using the general variance-based metric to equally aggregate cost, a new content-adaptive cost aggregation mechanism based on the similarity of the neighboring surface normal is designed for reliable cost aggregation. To the best of our knowledge, the proposed work is the first trainable network that leverages surface normal as guidance to capture neighboring pixel-visibility, which is an effective supplement to existing depth/normal estimation frameworks. Experimental results indicate that our method can not only achieve accurate depth estimation for scene perception but also make no concession to the real-time performance and limited memory bottleblock. Multiple-view stereo (MVS) aims to reconstruct the dense 3D representations of scenes. It is widely used in the fields of industrial measurement, autonomous driving, and robotic navigation. To mitigate the error of depth estimation in challenging scenarios, this work proposes a two-stage multi-view stereo network for fast and accurate depth estimation. Our method is the first trainable network that leverages surface normal as pixel-visibility guidance to aggregate reliable cost, which could achieve accurate depth estimation and provide the perception ability for the robot. The proposed method has great potential in the fields of 3D reconstruction, industrial measurement, and robotic navigation to estimate real-time and accurate depth with limited memory consumption.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
娜娜米发布了新的文献求助10
3秒前
5秒前
6秒前
9秒前
huahuahua发布了新的文献求助10
10秒前
lingjing完成签到,获得积分10
13秒前
迷路的谊完成签到 ,获得积分10
16秒前
萧雨墨发布了新的文献求助10
18秒前
深情安青的应助被娜娜米采纳,获得10
19秒前
huahuahua发布了新的文献求助10
26秒前
慈祥的蛋挞完成签到 ,获得积分10
31秒前
ubless607举报司源的求助涉嫌违规
32秒前
CipherSage的应助被xtc采纳,获得10
32秒前
36秒前
huahuahua发布了新的文献求助10
40秒前
41秒前
rex完成签到,获得积分10
44秒前
领导范儿的应助被luoshoahan采纳,获得10
45秒前
46秒前
科研通AI6.2的应助被amiee采纳,获得10
46秒前
46秒前
故事的角色完成签到,获得积分10
47秒前
47秒前
huahuahua发布了新的文献求助10
50秒前
50秒前
51秒前
53秒前
53秒前
Aria的应助被萧雨墨采纳,获得10
54秒前
LaKers发布了新的文献求助10
54秒前
luoshoahan发布了新的文献求助10
59秒前
torfun发布了新的文献求助10
59秒前
huahuahua发布了新的文献求助10
1分钟前
1分钟前
萧雨墨发布了新的文献求助10
1分钟前
1分钟前
1分钟前
fantasy的应助被科研通管家采纳,获得10
1分钟前
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8190037
求助须知:如何正确求助?哪些是违规求助? 9577165
关于积分的说明 21851818
捐赠科研通 7788131
什么是DOI,文献DOI怎么找? 3436021
关于科研通互助平台的介绍 2559910
邀请新用户注册赠送积分活动 2482768