Yu H, Chan S, Zhou X, Zhang X. SGFormer: Semantic-Geometry Fusion Transformer for Multi-modal 3D Panoptic Segmentation. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 13];39(9):9616-25. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/33042