Self-Supervised Deep Learning on Point Clouds by Reconstructing Space

By Jonathan Sauder, Bjarne Sievers. Neural Information Processing Systems, 2019

316 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ada50c9e8435a2ee77f630cc79b7fb57b7b2f47c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding (2022, background): “Recent line of works [17, 36, 42, 46, 48, 53, 64] introduce various pretext self-supervision tasks with the goal of learning rich semantic point attributes which eventually leads to high-level discriminative knowledge.”
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training (2022, unknown): “3D-GAN [52] 83.3 Latent-GAN [46] 85.7 SO-Net [25] 87.3 FoldingNet [57] 88.4 MAP-VAE [19] 88.4 VIP-GAN [18] 90.2 DGCNN + Jiasaw [43] 90.6 DGCNN + OcCo [49] 90.7 DGCNN + CrossPoint [2] 91.2 Transformer + OcCo [60] 89.6 Point-BERT [60] 87.4 Point-M2AE 92.9 Improvement +1.7 1 , the extra spatial noises…”
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding (2020, methodology): “Previous works on unsupervised 3D representation learning [1, 16, 74, 21, 36, 67, 22, 53] mainly focused on ShapeNet [7], a dataset of single-object CAD models.”
Masked Autoencoders for Point Cloud Self-supervised Learning (2022, background): “SSL for Point Cloud SSL has also been widely studied for point cloud representation learning [41,58,48,36,1,20,52,34,13,51].”
Point Transformer V3: Simpler, Faster, Stronger (2023, background): “While major efforts in 3D representation learning focused on individual objects [57, 68, 69, 87, 103], some recent advancements have redirected attention towards training on real-world scene-centric point clouds [30, 36, 91, 94, 107].”
Self-Supervised Pretraining of 3D Features on any Point-Cloud (2021, methodology): “Most methods on self-supervised learning focus on single 3D object representation with different applications to reconstruction, classification or part segmentation [1, 2, 25, 33, 35, 44, 49, 74, 99, 110].”
Unsupervised Point Cloud Pre-training via Occlusion Completion (2020, methodology): “In what follows we will show that unsupervised pre-training based on a simple self-supervised objective: completing occluded point clouds, produces weights that outperform [42] and [44] on downstream tasks.”