{"ID":2827208,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17817","arxiv_id":"2512.17817","title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","abstract":"While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by introducing Chorus, a multi-teacher pretraining framework that learns a holistic feed-forward 3D Gaussian Splatting (3DGS) scene encoder by distilling complementary signals from 2D foundation models. Chorus employs a shared 3D encoder and teacher-specific projectors to learn from language-aligned, generalist, and object-aware teachers, encouraging a shared embedding space that captures signals from high-level semantics to fine-grained structure. We evaluate Chorus on a wide range of tasks: open-vocabulary semantic and instance segmentation, linear and decoder probing, data-efficient supervision, as well as LLM-based Q\u0026A. Besides 3DGS, we also test Chorus on several benchmarks that only support point clouds by pretraining a variant using only Gaussian centers, colors, and estimated normals. Surprisingly, this encoder shows strong transfer and outperforms the point-cloud baseline while using 39.9 times fewer training scenes. Finally, we propose a render-and-distill adaptation that facilitates out-of-domain finetuning.","short_abstract":"While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by introducing Chorus, a multi-teacher pretraining framework that learns a holistic feed-forward 3D Gaussian Splatting (3DGS) scene encoder by...","url_abs":"https://arxiv.org/abs/2512.17817","url_pdf":"https://arxiv.org/pdf/2512.17817v3","authors":"[\"Yue Li\",\"Qi Ma\",\"Runyi Yang\",\"Mengjiao Ma\",\"Bin Ren\",\"Nikola Popovic\",\"Nicu Sebe\",\"Theo Gevers\",\"Luc Van Gool\",\"Danda Pani Paudel\",\"Martin R. Oswald\"]","published":"2025-12-19T17:22:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\"]","has_code":false}