Three-Dimensional Computer Vision: Reconstruction, Generation, and Intelligent Systems
A special issue of Journal of Imaging (ISSN 2313-433X). This special issue belongs to the section "Computer Vision and Pattern Recognition".
Deadline for manuscript submissions: 31 October 2026 | Viewed by 20
Special Issue Editors
Interests: 3D computer vision; deep learning; embodied AI
Interests: 3D computer vision (including mutli-view stereo, depth estimation, novel view synthesis and neural surface reconstruction) and physical AI (simulation and functional 3D generation)
Special Issue Information
Dear Colleagues,
Three-dimensional computer vision focuses on processing and understanding 3D data from images, videos, or multimodal sensory inputs. Over the past decades, the field has made substantial progress and has been widely applied in smartphones, AR/VR systems, robotics, autonomous driving, and industrial inspection. A core problem in 3D computer vision is 3D reconstruction, which aims to transform real-world observations into accurate digital 3D representations, enabling a wide range of downstream applications.
To overcome the limitation of scarce real-world 3D data and to advance AI-generated content (AIGC), 3D generation has emerged as a rapidly growing research direction, achieving notable success in object- and scene-level generation, 3D editing, digital twins, and simulation for robotics, design, and engineering. Meanwhile, recent advances in foundation models and multimodal learning have significantly enhanced the generalization, scalability, and robustness of 3D vision systems.
With the rapid development of robotics, autonomous systems, and immersive technologies, reliable and explainable 3D perception has become increasingly essential. This trend highlights the importance of applying 3D computer vision techniques to real-world scenarios, including navigation, manipulation, augmented and virtual reality, industrial inspection, and intelligent systems operating in complex and dynamic environments.
This Special Issue invites contributions from researchers to present their latest advancements, propose solutions to address open challenges, and outline future research directions in 3D computer vision. Submissions may include, but are not limited to, the following topics:
- Foundation models for 3D vision and multimodal learning
- Three-dimensional generation of objects and scenes with geometric consistency
- Understanding of static and dynamic scenes
- Self-supervised and weakly supervised learning in 3D vision
- Industrial applications of 3D vision (inspection, metrology, logistics)
- Three-dimensional generation for design, engineering, and digital twins
- Three-dimensional vision for augmented, virtual, and mixed reality
- Three-dimensional perception for autonomous vehicles and intelligent systems
- Explainable, reliable, and robust 3D AI in real-world conditions
Dr. Fangjinhua Wang
Dr. Qingshan Xu
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- three-dimensional computer vision
- three-dimensional reconstruction
- three-dimensional generation
- foundation models
- scene understanding
- robotics and autonomous systems
- robust 3D AI
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
