{"ID":2828117,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15577","arxiv_id":"2512.15577","title":"MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors","abstract":"In this paper, we focus on online zero-shot monocular 3D instance segmentation, a novel practical setting where existing approaches fail to perform because they rely on posed RGB-D sequences. To overcome this limitation, we leverage CUT3R, a recent Reconstructive Foundation Model (RFM), to provide reliable geometric priors from a single RGB stream. We propose MoonSeg3R, which introduces three key components: (1) a self-supervised query refinement module with spatial-semantic distillation that transforms segmentation masks from 2D visual foundation models (VFMs) into discriminative 3D queries; (2) a 3D query index memory that provides temporal consistency by retrieving contextual queries; and (3) a state-distribution token from CUT3R that acts as a mask identity descriptor to strengthen cross-frame fusion. Experiments on ScanNet200 and SceneNN show that MoonSeg3R is the first method to enable online monocular 3D segmentation and achieves performance competitive with state-of-the-art RGB-D-based systems. Our code is available at https://github.com/VICO-UoE/MoonSeg3R.","short_abstract":"In this paper, we focus on online zero-shot monocular 3D instance segmentation, a novel practical setting where existing approaches fail to perform because they rely on posed RGB-D sequences. To overcome this limitation, we leverage CUT3R, a recent Reconstructive Foundation Model (RFM), to provide reliable geometric pr...","url_abs":"https://arxiv.org/abs/2512.15577","url_pdf":"https://arxiv.org/pdf/2512.15577v2","authors":"[\"Zhipeng Du\",\"Duolikun Danier\",\"Jan Eric Lenssen\",\"Hakan Bilen\"]","published":"2025-12-17T16:36:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":605850,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2828117,"paper_url":"https://arxiv.org/abs/2512.15577","paper_title":"MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors","repo_url":"https://github.com/VICO-UoE/MoonSeg3R","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}