Li Z, Chen Z, Li A, Fang L, Jiang Q, Liu X, et al. SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-training for Spatial-Aware Visual Representations. AAAI [Internet]. 2022 Jun. 28 [cited 2026 May 8];36(2):1500-8. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/20040