Problem
Research questions and friction points this paper is trying to address.
Next-Best-View Selection
Privacy-Preserving
3D Gaussian Splatting
Multi-Robot Systems
Distributed Mapping
TRACE: Privacy-Preserving Next-Best-View Selection over Distributed 3D Gaussian-Splat Maps
🤖 AI Summary
This study addresses the challenge of next-best-view selection in multi-robot collaboration, where map sharing is restricted by privacy constraints. We propose TRACE, a protocol that decomposes transmittance and radiance aggregations to transmit only depth-binned statistics. By integrating 3D Gaussian Splatting, expected information gain optimization, and gradient computation on the SO(3) manifold, TRACE enables distributed ray tracing and collaborative view planning without exchanging raw data. Experimental results demonstrate constant communication overhead with controllable reconstruction error. In Habitat-Sim simulations, 83.3% of decision deviations remain below 15°, and the achieved viewpoint quality reaches 97.9% of that obtained by centralized approaches.
📝 Abstract
Share the light, not the map. We study next-best-view selection for a team of robots, each of which builds its own 3D Gaussian Splatting map and keeps it private. A robot picks the view with the largest expected information gain (EIG) about the splats along its own path. This gain depends on the other maps. Their splats occlude its own and shine behind them, so the gain has to be evaluated against the pooled map. No robot has this map. We show that the coupling passes through only two ray quantities, the transmittance in front of a splat and the radiance behind it, and that both are sums over the hits of the ray. Hence, they decompose across the robots, and each robot sums them over depth bins in its own map, along the rays of a candidate view, and sends the sums with their pose derivatives. The robot planning the view turns them into its EIG and gradient on SO(3). Transmittance and Radiance Aggregates, communicated for the EIG, give the protocol its name: TRACE. No robot shares its splats, and the message size does not grow with a map. We prove that the reconstruction is exact unless a depth bin behind a splat mixes hits of two robots, and we bound the error otherwise. Over 100 next-best-view decisions in Habitat-Sim, TRACE picks a heading within 15 degrees of the centralized one in 83.3% of the cases, and its views reach 97.9% of the centralized EIG.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Privacy-Preserving
Next-Best-View Selection
3D Gaussian Splatting
Distributed Multi-Robot
Expected Information Gain
🔎 Similar Papers
No similar papers found.
