SRNSD: Structure-Regularized Night-time Self-supervised Monocular Depth Estimation for Outdoor Scenes

人工智能 计算机视觉 单眼 计算机科学 模式识别(心理学)
作者
Runmin Cong,Chunlei Wu,Xibin Song,Wei Zhang,Sam Kwong,Hongdong Li,Pan Ji
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tip.2024.3465034
摘要

Deep CNNs have achieved impressive improvements for night-time self-supervised depth estimation form a monocular image. However, the performance degrades considerably compared to day-time depth estimation due to significant domain gaps, low visibility, and varying illuminations between day and night images. To address these challenges, we propose a novel night-time self-supervised monocular depth estimation framework with structure regularization, i.e., SRNSD, which incorporates three aspects of constraints for better performance, including feature and depth domain adaptation, image perspective constraint, and cropped multi-scale consistency loss. Specifically, we utilize adaptations of both feature and depth output spaces for better night-time feature extraction and depth map prediction, along with high- and low-frequency decoupling operations for better depth structure and texture recovery. Meanwhile, we employ an image perspective constraint to enhance the smoothness and obtain better depth maps in areas where the luminosity jumps change. Furthermore, we introduce a simple yet effective cropped multi-scale consistency loss that utilizes consistency among different scales of depth outputs for further optimization, refining the detailed textures and structures of predicted depth. Experimental results on different benchmarks with depth ranges of 40m and 60m, including Oxford RobotCar dataset, nuScenes dataset and CARLA-EPE dataset, demonstrate the superiority of our approach over state-of-the-art night-time self-supervised depth estimation approaches across multiple metrics, proving our effectiveness.
最长约 10秒,即可获得该文献文件

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
活力的泥猴桃完成签到 ,获得积分10
1秒前
曲奇饼干发布了新的文献求助10
1秒前
hfy完成签到,获得积分10
2秒前
4秒前
悦耳的母鸡完成签到,获得积分10
4秒前
luffy189完成签到 ,获得积分10
4秒前
6秒前
6秒前
6秒前
6秒前
7秒前
小白菜完成签到 ,获得积分10
7秒前
森sen发布了新的文献求助10
8秒前
9秒前
9秒前
wang完成签到,获得积分10
10秒前
Wang Mu发布了新的文献求助10
10秒前
mmm发布了新的文献求助10
11秒前
makimaki发布了新的文献求助10
12秒前
MaoMao发布了新的文献求助10
12秒前
12秒前
12秒前
长尾巴的人类完成签到,获得积分10
13秒前
着急的笑旋完成签到,获得积分10
16秒前
周杰完成签到,获得积分10
16秒前
科研通AI5应助阿光采纳,获得10
17秒前
gezid完成签到 ,获得积分10
18秒前
18秒前
贪玩半蕾发布了新的文献求助10
19秒前
xx发布了新的文献求助10
19秒前
hanleiharry1发布了新的文献求助10
20秒前
20秒前
tutu完成签到,获得积分10
21秒前
Lucas应助wanhe采纳,获得10
22秒前
23秒前
23秒前
23秒前
Shell完成签到,获得积分10
23秒前
科目三应助科研猫采纳,获得10
23秒前
24秒前
高分求助中
Production Logging: Theoretical and Interpretive Elements 2700
Mechanistic Modeling of Gas-Liquid Two-Phase Flow in Pipes 2500
Kelsen’s Legacy: Legal Normativity, International Law and Democracy 1000
Handbook on Inequality and Social Capital 800
Conference Record, IAS Annual Meeting 1977 610
Interest Rate Modeling. Volume 3: Products and Risk Management 600
Interest Rate Modeling. Volume 2: Term Structure Models 600
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3546536
求助须知:如何正确求助?哪些是违规求助? 3123667
关于积分的说明 9356348
捐赠科研通 2822331
什么是DOI,文献DOI怎么找? 1551314
邀请新用户注册赠送积分活动 723326
科研通“疑难数据库(出版商)”最低求助积分说明 713699