{"ID":2882697,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09626","arxiv_id":"2508.09626","title":"Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation","abstract":"In the task of 3D Aerial-view Scene Semantic Segmentation (3D-AVS-SS), traditional methods struggle to address semantic ambiguity caused by scale variations and structural occlusions in aerial images. This limits their segmentation accuracy and consistency. To tackle these challenges, we propose a novel 3D-AVS-SS approach named SAD-Splat. Our method introduces a Gaussian point drop module, which integrates semantic confidence estimation with a learnable sparsity mechanism based on the Hard Concrete distribution. This module effectively eliminates redundant and semantically ambiguous Gaussian points, enhancing both segmentation performance and representation compactness. Furthermore, SAD-Splat incorporates a high-confidence pseudo-label generation pipeline. It leverages 2D foundation models to enhance supervision when ground-truth labels are limited, thereby further improving segmentation accuracy. To advance research in this domain, we introduce a challenging benchmark dataset: 3D Aerial Semantic (3D-AS), which encompasses diverse real-world aerial scenes with sparse annotations. Experimental results demonstrate that SAD-Splat achieves an excellent balance between segmentation accuracy and representation compactness. It offers an efficient and scalable solution for 3D aerial scene understanding.","short_abstract":"In the task of 3D Aerial-view Scene Semantic Segmentation (3D-AVS-SS), traditional methods struggle to address semantic ambiguity caused by scale variations and structural occlusions in aerial images. This limits their segmentation accuracy and consistency. To tackle these challenges, we propose a novel 3D-AVS-SS appro...","url_abs":"https://arxiv.org/abs/2508.09626","url_pdf":"https://arxiv.org/pdf/2508.09626v2","authors":"[\"Xu Tang\",\"Junan Jia\",\"Yijing Wang\",\"Jingjing Ma\",\"Xiangrong Zhang\"]","published":"2025-08-13T08:57:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}