Related papers: Unsupervised Point Cloud Pre-Training via Occlusio…

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D…

Real-world environment-derived point clouds invariably exhibit noise across varying modalities and intensities. Hence, point cloud denoising (PCD) is essential as a preprocessing step to improve downstream task performance. Deep learning…

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such…

In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…

We propose a novel convolutional operator for the task of point cloud completion. One striking characteristic of our approach is that, conversely to related work it does not require any max-pooling or voxelization operation. Instead, the…

Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with…

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary…

It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or…

In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames are high-profile concerns recently. By analyzing tasks above,…

Strong evidence suggests that humans perceive the 3D world by parsing visual scenes and objects into part-whole hierarchies. Although deep neural networks have the capability of learning powerful multi-level representations, they can not…

Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper primarily discusses point cloud learning in…

Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud…

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…

Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector.…

Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this…

Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc.…

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details, given partial input, a…

In this paper, we introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion without requiring iterative spatial propagations. Specifically, we first enhance a baseline convolutional depth…

Masked autoencoder has been widely explored in point cloud self-supervised learning, whereby the point cloud is generally divided into visible and masked parts. These methods typically include an encoder accepting visible patches…

We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image. We demonstrate that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks,…