App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 4

Patch-based fusion for high-resolution monocular depth estimation

Yin Qian1,2
Chen Yunhao1,2
Zhao Li1,2
Yang Songyan1,2
Tang Jianing1,2
1. School of Electrical and Information Engineering, Yunnan Minzu University, Kunming 650500, China
2. Yunnan Key Laboratory of Unmanned Autonomous Systems, Kunming 650500, China
DOI: 10.19734/j.issn.1001-3695.2025.07.0310

Abstract

High-resolution monocular depth estimation suffers from poor generalization of low-resolution trained models, leading to high-frequency detail loss and error propagation, as well as noise and holes in consumer-grade depth maps. This work proposes a patch-based fusion framework, DA-ZoeDepth, to address these issues. We design the DA-ZoeDepth model by combining the DPT-DINOV encoder from Depth-Anything with the ZoeDepth decoder to perform global coarse and patch-based fine depth estimation. A High–Low Frequency Feature Fusion Module (HLAEM) and a Guided Fusion Network (GFN) are developed to integrate global and local depth maps seamlessly, while a consistency loss (Lconsist) is introduced to improve patch boundary continuity. Experiments on UnrealStereo4K and MVS-Synth datasets demonstrate that our method reduces relative error (REL) by 0.005 and 0.0092, and decreases RMSE by 0.046 and SiLog by 1.189 compared to BoostingDepth. Superior zero-shot generalization is observed on the Middlebury 2021 dataset. The proposed approach significantly enhances depth estimation accuracy and structural consistency in high-resolution scenarios, offering a robust and efficient solution for applications such as AR/VR and autonomous driving.

Foundation Support

国家自然科学基金资助项目(62105279,62401499)
云南省应用基础研究基金资助项目(202201AU070047,202401CF070074)
云南省重大科技项目及重点研发计划(202403ZC380002)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.07.0310
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 4

Publish History

[2025-12-19] Accepted Paper

Cite This Article

尹倩, 陈云浩, 赵莉, 等. 基于分块融合的高分辨率单目深度估计 [J]. 计算机应用研究, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.07.0310. (Yin Qian, Chen Yunhao, Zhao Li, et al. Patch-based fusion for high-resolution monocular depth estimation [J]. Application Research of Computers, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.07.0310. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)