Agents
ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting
arXiv:2607.15542v2 Announce Type: replace Abstract: On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VB
arXiv:2607.15542v2 Announce Type: replace Abstract: 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. We also improve novel-view synthesis quality using an exact renderer with no added training costs.
Related
- 3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
- Supercharging Thermal Gaussian Splatting with Depth Estimation
- Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance
- SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation
- DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction
Source: arXiv cs.CV | 2026-09-01