ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting
Quick Answer
This paper shows that ImprovedVBGS accelerates real-time continual 3D reconstruction, achieving a 1680x speed-up in latency from ~84.0s to ~0.050s on RTX 3070 Ti, while maintaining reconstruction quality.
Quick Take
This framework enhances Variational Bayes Gaussian Splatting through spatially truncated inference and improved reassignment techniques, making it suitable for robotics and autonomous navigation applications.
Key Points
- Achieves 1680x speed-up in per-frame latency for real-time applications.
- Reduces mean latency from ~84.0s to ~0.050s on RTX 3070 Ti.
- Utilizes spatially truncated variational inference for efficiency.
- Improves reassignment process by eliminating dynamic recompilation.
- Maintains high reconstruction quality despite accelerated processing.
Paper Resources
📖 Reader Mode
~2 min readAbstract:On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VBGS) enables continual learning without replay buffers using Coordinate Ascent Variational Inference (CAVI), but its per-frame iterations over all observed points make it too slow for real-time use with strict memory and latency requirements. We present ImprovedVBGS, an accelerated framework for on-the-fly continual reconstruction. This is achieved primarily through (i) spatially truncated variational inference, and (ii) improved reassignment that uses forwarding, truncation and eliminates wasteful dynamic recompilation. On the NeRF synthetic dataset, we reduce mean per-frame latency from ~84.0 s to ~0.050 s on an RTX 3070 Ti, a 1680x speed-up while maintaining reconstruction quality.
| Comments: | 5 pages, 4 figure. Technical Report. This work introduces ImprovedVBGS, accelerated continual learning for 3D Gaussian Splatting based Reconstruction. Code available at [this https URL](this https URL) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO) |
| Cite as: | arXiv:2607.15542 [cs.CV] |
| (or arXiv:2607.15542v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.15542 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Damani Mguni-Coker [view email]
[v1]
Fri, 17 Jul 2026 01:24:25 UTC (6,320 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.