Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation

Herrera-Granda, Erick P.; Torres-Cantero, Juan C.; Herrera-Granda, Israel D.; Lucio-Naranjo, José F.; Rosales, Andrés; Revelo-Fuelagán, Javier; Peluffo-Ordóñez, Diego H.

doi:10.3390/math13203330

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation

by

Erick P. Herrera-Granda

^1,2,3,*

,

Juan C. Torres-Cantero

⁴

,

Israel D. Herrera-Granda

⁵

,

José F. Lucio-Naranjo

^1,2

,

Andrés Rosales

⁶

,

Javier Revelo-Fuelagán

⁷

and

Diego H. Peluffo-Ordóñez

^3,8,9,*

¹

Department of Informatics and Computer Science, Escuela Politécnica Nacional, Quito 170525, Ecuador

²

Numerical Simulation and Computational Analysis Laboratory, LASINAC, Escuela Politécnica Nacional, Quito 170525, Ecuador

³

SDAS Research Group, Ben Guerir 43150, Morocco

⁴

Virtual Reality Laboratory, ETSIIT, Department of Computer Languages and Systems, University of Granada, 18071 Granada, Spain

⁵

Administration and Business Economics, Foreign Trade Program, Faculty of International Trade and Integration, Universidad Politécnica Estatal del Carchi, Calle Antisana y Av. Universitaria, 040102 Tulcán, Ecuador

⁶

Departamento de Automatización y Control Industrial, GIECAR, Escuela Politécnica Nacional, Quito 170525, Ecuador

⁷

Department of Electronic Engineering, Universidad de Nariño, Pasto 52001, Colombia

⁸

College of Computing, Mohammed VI Polytechnic University, Rachid, Ben Guerir 43150, Morocco

⁹

Universidad Ecotec, Investigación, Samborondón 092302, Ecuador

^*

Authors to whom correspondence should be addressed.

Mathematics 2025, 13(20), 3330; https://doi.org/10.3390/math13203330

Submission received: 11 August 2025 / Revised: 2 October 2025 / Accepted: 10 October 2025 / Published: 19 October 2025

(This article belongs to the Section E1: Mathematics and Computer Science)

Download Versions Notes

Abstract

In recent years, SLAM, visual odometry, and structure-from-motion approaches have widely addressed the problems of 3D reconstruction and ego-motion estimation. Of the many input modalities that can be used to solve these ill-posed problems, the pure visual alternative using a single monocular RGB camera has attracted the attention of multiple researchers due to its low cost and widespread availability in handheld devices. One of the best proposals currently available is the Direct Sparse Odometry (DSO) system, which has demonstrated the ability to accurately recover trajectories and depth maps using monocular sequences as the only source of information. Given the impressive advances in single-image depth estimation using neural networks, this work proposes an extension of the DSO system, named DeepDSO. DeepDSO effectively integrates the state-of-the-art NeW CRF neural network as a depth estimation module, providing depth prior information for each candidate point. This reduces the point search interval over the epipolar line. This integration improves the DSO algorithm’s depth point initialization and allows each proposed point to converge faster to its true depth. Experimentation carried out in the TUM-Mono dataset demonstrated that adding the neural network depth estimation module to the DSO pipeline significantly reduced rotation, translation, scale, start-segment alignment, end-segment alignment, and RMSE errors.

Keywords: CNN direct sparse odometry; monocular visual odometry; monocular 3D reconstruction; monocular ego-motion; pure visual odometry

Share and Cite

MDPI and ACS Style

Herrera-Granda, E.P.; Torres-Cantero, J.C.; Herrera-Granda, I.D.; Lucio-Naranjo, J.F.; Rosales, A.; Revelo-Fuelagán, J.; Peluffo-Ordóñez, D.H. Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation. Mathematics 2025, 13, 3330. https://doi.org/10.3390/math13203330

AMA Style

Herrera-Granda EP, Torres-Cantero JC, Herrera-Granda ID, Lucio-Naranjo JF, Rosales A, Revelo-Fuelagán J, Peluffo-Ordóñez DH. Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation. Mathematics. 2025; 13(20):3330. https://doi.org/10.3390/math13203330

Chicago/Turabian Style

Herrera-Granda, Erick P., Juan C. Torres-Cantero, Israel D. Herrera-Granda, José F. Lucio-Naranjo, Andrés Rosales, Javier Revelo-Fuelagán, and Diego H. Peluffo-Ordóñez. 2025. "Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation" Mathematics 13, no. 20: 3330. https://doi.org/10.3390/math13203330

APA Style

Herrera-Granda, E. P., Torres-Cantero, J. C., Herrera-Granda, I. D., Lucio-Naranjo, J. F., Rosales, A., Revelo-Fuelagán, J., & Peluffo-Ordóñez, D. H. (2025). Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation. Mathematics, 13(20), 3330. https://doi.org/10.3390/math13203330

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Deep-DSO: Improving Mapping of Direct Sparse Odometry Using CNN-Based Single-Image Depth Estimation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI