Human Motion Capture and 3D Reconstruction

Dear Colleagues,

This Special Issue focuses on recent advances in human motion capture and 3D reconstruction, with particular emphasis on 3D human avatar generation, human pose estimation, and the integration of multiple data sources. These directions are fundamental to enabling accurate, realistic, and scalable digital human representations, with applications spanning computer vision, computer graphics, virtual and augmented reality, gaming, robotics, and healthcare. The Special Issue highlights methods that reconstruct dynamic human motion and appearance from heterogeneous inputs such as monocular and multi-view RGB images, depth sensors, inertial measurement units (IMUs), LiDAR, and other wearable or environmental sensing systems.

The scope of this topical collection covers the full pipeline of human-centric 3D understanding, including 2D/3D pose estimation, multimodal data fusion, parametric and neural human body modeling, and high-fidelity avatar reconstruction. Special attention is given to approaches that effectively combine multiple data modalities to improve robustness, accuracy, and generalization in challenging real-world scenarios. The Special Issue also emphasizes recent advances in neural rendering and 3DGS-based representations, which enable efficient, photorealistic rendering of dynamic human scenes. Key challenges of interest include handling occlusions, noisy or incomplete data, cross-domain adaptation, synchronization across sensors, and real-time performance.

The purpose of this Special Issue is to provide a comprehensive platform for presenting cutting-edge research that bridges motion understanding, multimodal sensing, and realistic human reconstruction. By integrating pose estimation, avatar generation, and 3DGS-based rendering within unified frameworks, the collection aims to promote solutions that leverage complementary data sources for improved performance and scalability. It also seeks to encourage interdisciplinary collaboration and highlight methods that are both theoretically sound and practically deployable in real-world applications.

This collection will usefully supplement the existing literature by consolidating recent developments that are often fragmented across separate research communities, including computer vision, graphics, and sensing systems. While traditional studies have typically focused on single-modality inputs or isolated tasks, this Special Issue emphasizes the growing importance of multimodal fusion and end-to-end pipelines. By incorporating contributions that exploit diverse data sources alongside emerging rendering techniques such as 3DGS, it provides an updated and integrated perspective on next-generation human motion capture and 3D reconstruction systems.

Dr. Zheheng Jiang
Guest Editor

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. 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.

• human motion capture
• 3D reconstruction
• human pose estimation
• 3D human avatars
• 3D Gaussian splatting
• multimodal fusion
• neural rendering
• deep learning
• digital humans
• computer vision