Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.0
2.9
Journals
Electronics
Special Issues
Advances in 3D Computer Vision and 3D Data Processing
share announcement

Advances in 3D Computer Vision and 3D Data Processing

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 1741

Editors

Prof. Dr. Časlav Livada

E-Mail Website
Guest Editor
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University in Osijek, Kneza Trpimira 2B, 31000 Osijek, Croatia
Interests: 2D and 3D processing; machine learning; AI; virtual and augmented reality
Prof. Dr. Tomislav Keser

E-Mail Website
Guest Editor
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University in Osijek, Kneza Trpimira 2B, 31000 Osijek, Croatia
Interests: electronics; machine vision; computer vision; computer architecture; embedded computer systems; robotics
Dr. Linbo Qiao

E-Mail
Guest Editor
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China
Interests: online and distributed optimization; multimodal large language models

Special Issue Information

Dear Colleagues,

This Special Issue, “Advances in 3D Computer Vision and 3D Data Processing”, aims to highlight cutting-edge research and technological advancements in the rapidly evolving domains of 3D computer vision and data processing. With the increasing demand for precise 3D data acquisition, analysis, and application across diverse fields such as robotics, augmented reality (AR), virtual reality (VR), healthcare, and autonomous systems, this Special Issue seeks to provide a platform for innovative solutions addressing current challenges and exploring new possibilities.

The scope of this Special Issue encompasses a wide range of topics, including but not limited to 3D object recognition, scene reconstruction, multi-view geometry, depth estimation, and point cloud processing. It also focuses on advancements in machine learning and artificial intelligence techniques that enhance the accuracy, efficiency, and scalability of 3D vision systems. Contributions on novel algorithms for 3D data fusion, segmentation, registration, and geometric modeling are particularly encouraged. Additionally, we welcome research addressing practical challenges such as handling large-scale datasets, improving computational efficiency, and ensuring robustness in real-world applications.

By gathering high-quality research articles, reviews, and case studies, this Special Issue aims to foster collaboration among researchers from academia and industry. It seeks to advance the theoretical foundations of 3D computer vision while promoting its practical applications in areas like smart manufacturing, digital twins, autonomous navigation, and immersive technologies. This collection will serve as a valuable resource for researchers and practitioners striving to push the boundaries of what is achievable with 3D vision and data processing technologies.

Topic list:

  1. 3d object recognition and classification;
  2. Point cloud processing and analysis;
  3. Scene reconstruction and depth estimation;
  4. Generative AI for 3D model creation;
  5. Multi-view geometry and stereo vision techniques;
  6. Neural representations for 3D data (e.g., neural fields, NeRFs);
  7. Applications of 3D vision in AR/VR and the metaverse;
  8. Efficient algorithms for large-scale 3D data fusion;
  9. Robustness and security in 3D computer vision systems;
  10. Evaluation metrics and benchmarks for 3D vision algorithms;
  11. Parallel and distributed computing for 3D data processing.

Prof. Dr. Časlav Livada
Prof. Dr. Tomislav Keser
Dr. Linbo Qiao
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly 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 2400 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

  • 3D object recognition
  • point cloud processing
  • scene reconstruction
  • depth estimation

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.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

23 pages, 2862 KB  
Article
AMP: Automatic Modality-Aware Parallelization with Hidden-Dimension Tensor Parallelism for Multi-Modal 3D Biological Models
by Kailin Zhang, Hao Zheng and Lang Yuan
Electronics 2026, 15(13), 2769; https://doi.org/10.3390/electronics15132769 - 23 Jun 2026
Viewed by 246
Abstract
Three-dimensional (3D) spatial interaction data are fundamental to understanding genome architecture. Multi-modal deep learning models that jointly learn from 3D spatial data and orthogonal modalities, such as gene expression, face a critical computational challenge: the 3D spatial modality dominates computation by over one [...] Read more.
Three-dimensional (3D) spatial interaction data are fundamental to understanding genome architecture. Multi-modal deep learning models that jointly learn from 3D spatial data and orthogonal modalities, such as gene expression, face a critical computational challenge: the 3D spatial modality dominates computation by over one order of magnitude, creating a structural memory bottleneck that renders heavyweight model instances untrainable on single GPU. Existing distributed training methods rely on cost-model searching and treat model components uniformly, overlooking modality-specific memory asymmetries. We propose Automatic Modality-aware Parallelization (AMP), a framework that diagnoses memory bottlenecks from data configuration signals and prescribes a set of five strategies. At the core of this framework is a hidden-dimension tensor parallelism strategy (S5) that partitions the 3D decoder’s hidden dimension across GPUs, transforming five non-standard operators into sharded forms with formal equivalence proofs. Evaluated on Hi-C data and RNA-seq from the HiRES single-cell mouse brain dataset across lightweight and heavyweight configurations, AMP converts out-of-memory (OOM) failures into successful training runs. Scaling from four to eight GPUs under heavyweight configurations, the 500 kb and 100 kb variants achieve 2.0× and 3.8× training speedups respectively, with mathematical equivalence to single GPU computation guaranteed by formal proofs. Full article
(This article belongs to the Special Issue Advances in 3D Computer Vision and 3D Data Processing)
►▼ Show Figures

Figure 1

21 pages, 3029 KB  
Article
ParaChromo: Scalable and Seam-Coherent Inference for 3D Genome Diffusion
by Xialin Su, Mingxiang Zhu, Wei Shang and Zhixin Ou
Electronics 2026, 15(13), 2750; https://doi.org/10.3390/electronics15132750 - 23 Jun 2026
Viewed by 123
Abstract
Diffusion models for 3D genome structures make inference an ensemble-generation and tiling problem. In the released ChromoGen workflow, millions of independent denoising trajectories are executed through a single-GPU path, while overlapping genomic windows are sampled without enforcing consistency of their shared physical interval. [...] Read more.
Diffusion models for 3D genome structures make inference an ensemble-generation and tiling problem. In the released ChromoGen workflow, millions of independent denoising trajectories are executed through a single-GPU path, while overlapping genomic windows are sampled without enforcing consistency of their shared physical interval. We introduce ParaChromo, a parallel inference framework for conditioned, tiled 3D genome diffusion workloads built around the trained diffusion U-Net and distance-map interface. ParaChromo organizes the workload into three inference-layer modules: a workload-dispatch module schedules region, guidance, and sample chunks across worker groups; an encoder-aware sharded-conditioning module scales and shards the EPCOT front end with FSDP while keeping the inner-loop U-Net replicated; and a seam-coherent tiled-synchronization module projects the shared 12-bead overlap of adjacent reverse chains in distance-map space. On eight A6000 GPUs, the combined reduced-step and task-parallel systems path raises throughput from 2.356±0.003 to 235.71±1.120 samples/s, a 100.04±0.486-fold gain over the released single-GPU baseline. The reduced-step setting is supported by a sweep from 50 to 1000 DDIM steps, where distance-distribution and Hi-C-based metrics remain stable across four chromosomes. For the synchronization module, the chr22 seam discrepancy falls from 150.9 pm to 7.9 pm, while matched internal and Hi-C-based quality metrics are preserved. The synchronized chr22 run also gives a chromosome-scale coordinate rendering over 32 paper-aligned tiles. Together, these results show that conditioned, tiled 3D genome diffusion can be executed as a scalable workload when throughput parallelism, sampler length, encoder placement, and spatial consistency are treated as separate but compatible constraints. Full article
(This article belongs to the Special Issue Advances in 3D Computer Vision and 3D Data Processing)
►▼ Show Figures

Figure 1

23 pages, 11947 KB  
Article
Geometry-Consistency-Guided Unsupervised Domain Adaptation Framework for Cross-Voltage Transmission-Line Point-Cloud Semantic Segmentation
by Kun Ji, Hongwu Tan, Dabing Yang, Pu Wang, Di Cao, Yuan Gao and Zhou Yang
Electronics 2026, 15(2), 378; https://doi.org/10.3390/electronics15020378 - 15 Jan 2026
Cited by 1 | Viewed by 722
Abstract
Semantic segmentation of transmission-line point clouds is fundamental to intelligent power inspection and grid asset management, as segmentation accuracy directly influences defect detection and facility assessment tasks. However, transmission-line point clouds collected across different voltage levels often show significant variations in density and [...] Read more.
Semantic segmentation of transmission-line point clouds is fundamental to intelligent power inspection and grid asset management, as segmentation accuracy directly influences defect detection and facility assessment tasks. However, transmission-line point clouds collected across different voltage levels often show significant variations in density and geometric structure due to heterogeneous LiDAR sensors and flight configurations. Combined with the high cost of large-scale manual annotation, these factors limit the scalability of existing supervised segmentation methods. To overcome these challenges, we propose a geometry-consistency-guided unsupervised domain adaptation framework tailored for cross-voltage transmission-line point-cloud segmentation. The framework employs KPConvX as the backbone and integrates three progressive components. First, a geometric consistency constraint enhances robustness to spatial variations and enables extraction of structural features invariant across voltage levels. Second, a domain feature alignment module reduces distribution shifts through global feature transformation. Third, a minimum-entropy-based pseudo-label refinement strategy improves the reliability of pseudo-labels during self-training. Experiments on a multi-voltage transmission-line dataset demonstrate the effectiveness of the proposed method. With the KPConvX backbone, the framework achieves 66.1% mean Intersection over Union (mIoU) and 94.3% overall accuracy on the unlabeled 110 kV target domain, exceeding the source-only baseline by 15.6% mIoU and outperforming several state-of-the-art UDA methods. This work provides an efficient, annotation-friendly solution for cross-voltage point-cloud segmentation and offers a promising direction for domain adaptation in complex power-grid environments. Full article
(This article belongs to the Special Issue Advances in 3D Computer Vision and 3D Data Processing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop