{"ID":5439463,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T18:33:34.948478042Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30809","arxiv_id":"2606.30809","title":"GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping","abstract":"Existing 3D Gaussian Splatting (3DGS) systems distribute representation capacity uniformly across a scene, ignoring the fact that many downstream robotic tasks engage only a fraction of the reconstructed geometry. This causes valuable onboard compute to be allocated towards optimizing irrelevant parts of the scene, either limiting online capacity or under-optimizing the most relevant parts of the scene. We introduce GaussLite, a task-driven 3DGS mapping system that conditions its representation density on a natural-language task specification. Given a posed RGB-D stream and a task such as \"prepare to pick up the object on the desk,\" GaussLite uses a one-shot LLM parser to extract target and anchor objects, which are grounded per-frame by an open-vocabulary detector and segmented to produce per-pixel relevance masks in real time. The mapper allocates seeding density, gradient flow and scaling by task relevance. At matched Gaussian budget and real-time mapping at 4 Hz on resource-constrained hardware, GaussLite outperforms baselines on ROI PSNR on the Replica Dataset by an average +2.72 dB and on a real-hardware demonstration in indoor and outdoor settings by +2.23 dB. We further show that two task-specialized agents' maps can be fused into a single shared map via per-voxel voting on active-optimization counts in real time, outperforming concatenation by +3.42 dB while only sharing an average 7.08% of the map.","short_abstract":"Existing 3D Gaussian Splatting (3DGS) systems distribute representation capacity uniformly across a scene, ignoring the fact that many downstream robotic tasks engage only a fraction of the reconstructed geometry. This causes valuable onboard compute to be allocated towards optimizing irrelevant parts of the scene, eit...","url_abs":"https://arxiv.org/abs/2606.30809","url_pdf":"https://arxiv.org/pdf/2606.30809v1","authors":"[\"Annika Thomas\",\"Mason Peterson\",\"Jonathan P. How\"]","published":"2026-06-29T18:34:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Large Language Model\"]","has_code":false}