[Master's Thesis] - Egocentric Dynamic Neural Novel View Synthesis for the Operating Room

22.01.2026, Abschlussarbeiten, Bachelor- und Masterarbeiten

The Human-Centered Computing and Extended Reality Lab of the Professorship for Machine Intelligence in Orthopedics seeks applicants for a Master Thesis

Project Description

Dynamic novel view synthesis reconstructs environments over time, extending traditional static novel view synthesis techniques. Modern approaches, such as time-aware adaptations of Gaussian Splatting, can reconstruct in high quality. As part of a broader effort to reconstruct operating rooms and surgeries, this project aims to identify and improve the method for reconstructing egocentric video, such as that captured by head-mounted cameras worn by surgeons. You should survey and categorize existing methods. We also aim to explore potential improvements to temporal stability and performance, such as adaptive temporal anchors for dynamic scene geometry. We aim to create a test video dataset using cameras owned by the lab to explore egocentric reconstruction, in addition to what common public datasets offer.

Key Research Areas

• Reviewing state-of-the-art dynamic novel view synthesis techniques
• Categorize and experiment with existing approaches
• Prepare test video dataset
• Improve promising existing codebases

Technical Prerequisites (Or motivation to learn)

• Interest in AI-driven reconstruction and novel view synthesis
• Ability to understand and run AI codebases
• Proficiency in Python, Pytorch, and related technologies

Please send your transcript of records, CV and motivation to: Constantin Kleinbeck (constantin.kleinbeck@tum.de) with CC to hex-thesis.ortho@mh.tum.de

Literature
[1] J. Yan et al., “Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting,” in Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 16520–16531 [2] T. Li et al., “Neural 3D Video Synthesis from Multi-view Video,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA: IEEE, Jun. 2022, pp. 5511–5521. doi: 10.1109/CVPR52688.2022.00544. [3] A. Cao and J. Johnson, “HexPlane: A Fast Representation for Dynamic Scenes,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada: IEEE, Jun. 2023, pp. 130–141. doi: 10.1109/CVPR52729.2023.00021. [4] G. Wu et al., “4D Gaussian Splatting for Real-Time Dynamic Scene Rendering,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, Jun. 2024, pp. 20310–20320. doi: 10.1109/CVPR52733.2024.01920. [5] Y. Duan, F. Wei, Q. Dai, Y. He, W. Chen, and B. Chen, “4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes,” Jul. 02, 2024, arXiv: arXiv:2402.03307. doi: 10.48550/arXiv.2402.03307. [6] Z. Xu et al., “Representing Long Volumetric Video with Temporal Gaussian Hierarchy,” ACM Trans. Graph., vol. 43, no. 6, pp. 1–18, Dec. 2024, doi: 10.1145/3687919. [7] J. Wu et al., “Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene,” Mar. 16, 2025, arXiv: arXiv:2503.12307. doi: 10.48550/arXiv.2503.12307.

Kontakt: constantin.kleinbeck@tum.de