{"ID":2845144,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.03992","arxiv_id":"2511.03992","title":"Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation","abstract":"Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions across views. We propose CaRF (Camera-aware Referring Field), a camera-aware cross-view alignment framework for view-consistent referring in 3D Gaussian splatting. CaRF introduces Camera-conditioned Alignment Modulation (CAM) to inject camera geometry into Gaussian-text interactions, and Gaussian-level Cross-view Logit Alignment (GCLA) to explicitly align referring responses of the same Gaussians across calibrated views during training. By turning cross-view discrepancy into an optimizable objective, CaRF enables geometry-aware and view-consistent reasoning directly in the Gaussian space. Extensive experiments on three benchmarks demonstrate that CaRF achieves state-of-the-art performance, improving mIoU by 16.8%, 4.3%, and 2.0% on Ref-LERF, LERF-OVS, and 3D-OVS, respectively. Our code is available at https://github.com/eR3R3/CaRF.","short_abstract":"Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions across views. We propose CaRF (Camera-aware Referring Field), a camera-aware cro...","url_abs":"https://arxiv.org/abs/2511.03992","url_pdf":"https://arxiv.org/pdf/2511.03992v2","authors":"[\"Yuwen Tao\",\"Kanglei Zhou\",\"Xin Tan\",\"Yuan Xie\"]","published":"2025-11-06T02:24:04Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607346,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2845144,"paper_url":"https://arxiv.org/abs/2511.03992","paper_title":"Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation","repo_url":"https://github.com/eR3R3/CaRF","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}