paper-with-me

Papers

Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark

2021-08-09 · ICCV 2021 10 · Kun Wang, Zhenyu Zhang, Zhiqiang Yan, Xiang Li, Baobei Xu, Jun Li, Jian Yang

Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime benchmarks. However, they produce weird outputs in more challenging nighttime scenarios because of low visibility and varying illuminations, which bring weak textures and break brightness-consistency assumption, respectively. To address these problems, in this paper we propose a novel framework with several improvements: (1) we introduce Priors-Based Regularization to learn distribution knowledge from unpaired depth maps and prevent model from being incorrectly trained; (2) we leverage Mapping-Consistent Image Enhancement module to enhance image visibility and contrast while maintaining brightness consistency; and (3) we present Statistics-Based Mask strategy to tune the number of removed pixels within textureless regions, using dynamic statistics. Experimental results demonstrate the effectiveness of each component. Meanwhile, our framework achieves remarkable improvements and state-of-the-art results on two nighttime datasets.

📄 PDF Abstract BibTeX arXiv:2108.03830

Code (2)

w2kun/rnw 공식 구현 pytorch
ucaszyp/steps pytorch

Tasks

Depth EstimationImage EnhancementMonocular Depth Estimation

Similar Papers 제목 키워드 기반

Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation

2024-04-22 · Haolin Yang, Chaoqiang Zhao, Lu Sheng, Yang Tang

Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usu…

Depth EstimationDomain AdaptationMonocular Depth Estimation

GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation

2023-02-20 · Zezheng Zhang, Ryan K. Y. Chan, Kenneth K. Y. Wong

In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focu…

AllDepth EstimationMonocular Depth Estimation

DASP: Self-supervised Nighttime Monocular Depth Estimation with Domain Adaptation of Spatiotemporal Priors

2025-12-16 · Yiheng Huang, Junhong Chen, Anqi Ning, Zhanhong Liang 외 arxiv

Self-supervised monocular depth estimation has achieved notable success under daytime conditions. However, its performance deteriorates markedly at night due to low visibility and varying illumination, e.g., insufficient…

Monocular Depth EstimationDomain Adaptation

LAA-Net: A Physical-prior-knowledge Based Network for Robust Nighttime Depth Estimation

2024-12-05 · KeBin Peng, Haotang Li, Zhenyu Qi, Huashan Chen 외

Existing self-supervised monocular depth estimation (MDE) models attempt to improve nighttime performance by using GANs to transfer nighttime images into their daytime versions. However, this can introduce inconsistencie…

Depth EstimationMonocular Depth Estimation

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

2020-03-30 · CVPR 2020 6 · Jaime Spencer, Richard Bowden, Simon Hadfield

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize …

Depth EstimationMonocular Depth EstimationRepresentation Learning