Related papers: SimC3D: A Simple Contrastive 3D Pretraining Framew…

Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of…

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms…

Contrastive learning is a key technique of modern self-supervised learning. The broader accessibility of earlier approaches is hindered by the need of heavy computational resources (e.g., at least 8 GPUs or 32 TPU cores), which accommodate…

Self-supervised pre-training has achieved remarkable success in NLP and 2D vision. However, these advances have yet to translate to 3D data. Techniques like masked reconstruction face inherent challenges on unstructured point clouds, while…

Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks. However, due to the limited Text-3D data pairs, adapting the…

Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective…

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging. Many recent studies on point cloud pre-training, however, have overlooked the issue of incompleteness, where…

Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance…

In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships. However, learning semantic 3D scene graphs in a fully…

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be…

Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns. Adversarial contrastive learning (ACL) is considered an…

Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel…

Building a robust perception module is crucial for visuomotor policy learning. While recent methods incorporate pre-trained 2D foundation models into robotic perception modules to leverage their strong semantic understanding, they struggle…

Reconstructing 3D shapes from a single image plays an important role in computer vision. Many methods have been proposed and achieve impressive performance. However, existing methods mainly focus on extracting semantic information from…

Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored.…

3D model generation from single 2D RGB images is a challenging and actively researched computer vision task. Various techniques using conventional network architectures have been proposed for the same. However, the body of research work is…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D models, and no existing pre-training method is equally…