# Improving Continual Learning for Gaussian Splatting based Environments Reconstruction on Commercial Off-the-Shelf Edge Devices

arXiv: https://arxiv.org/abs/2603.08499 · HTML: https://mlsanity.com/paper/2603.08499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2311.11700/) (2023)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [CLNeRF: Continual Learning Meets NeRF](https://mlsanity.com/paper/2308.14816/) (2023)
- [RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction](https://mlsanity.com/paper/2510.06644/) (2025)
- [Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication](https://mlsanity.com/paper/2510.22718/) (2025)

## Built on by (most cited first, 1 of 1)

- [ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting](https://mlsanity.com/paper/2607.15542/) (2026)

## Abstract (arXiv)

Novel view synthesis (NVS) is increasingly relevant for edge robotics, where compact and incrementally updatable 3D scene models are needed for SLAM, navigation, and inspection under tight memory and latency budgets. Variational Bayesian Gaussian Splatting (VBGS) enables replay-free continual updates for the 3DGS algorithm by maintaining a probabilistic scene model, but its high-precision computations and large intermediate tensors make on-device training impractical. We present a precision-adaptive optimization framework that enables VBGS training on resource-constrained hardware without altering its variational formulation. We (i) profile VBGS to identify memory/latency hotspots, (ii) fuse memory-dominant kernels to reduce materialized intermediate tensors, and (iii) automatically assign operation-level precisions via a mixed-precision search with bounded relative error. Across the Blender, Habitat, and Replica datasets, our optimised pipeline reduces peak memory from 9.44 GB to 1.11 GB and training time from ~234 min to ~61 min on an A5000 GPU, while preserving (and in some cases improving) reconstruction quality of the state-of-the-art VBGS baseline. We also enable for the first time NVS training on a commercial embedded platform, the Jetson Orin Nano, reducing per-frame latency by 19x compared to 3DGS.