{"ID":2880816,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14036","arxiv_id":"2508.14036","title":"GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation","abstract":"We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation that casts the task as multi-view 2D mask prediction. Given a textureless object, we render normal and point maps from predefined viewpoints and accept simple 2D prompts - clicks or boxes - to guide part selection. These prompts are processed by a shared SAM2 backbone augmented with LoRA and residual geometry fusion, enabling view-specific reasoning while preserving pretrained priors. The predicted masks are back-projected to the object and aggregated across views. Our method enables fine-grained, part-specific control without requiring text prompts, per-shape optimization, or full 3D labels. In contrast to global clustering or scale-based methods, prompts are explicit, spatially grounded, and interpretable. We achieve state-of-the-art class-agnostic performance on PartObjaverse-Tiny and PartNetE, outperforming both slow optimization-based pipelines and fast but coarse feedforward approaches. Our results highlight a new paradigm: aligning the paradigm of 3D segmentation with SAM2, leveraging interactive 2D inputs to unlock controllability and precision in object-level part understanding.","short_abstract":"We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation that casts the task as multi-view 2D mask prediction. Given a textureless object, we render normal and point maps from predefined viewpoints and accept simple 2D prompts - clicks or boxes - to guide part selection. These prompts are processe...","url_abs":"https://arxiv.org/abs/2508.14036","url_pdf":"https://arxiv.org/pdf/2508.14036v2","authors":"[\"Ken Deng\",\"Yunhan Yang\",\"Jingxiang Sun\",\"Xihui Liu\",\"Yebin Liu\",\"Ding Liang\",\"Yan-Pei Cao\"]","published":"2025-08-19T17:58:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"LoRA\"]","has_code":false}