Related papers: Learning Latent Part-Whole Hierarchies for Point C…
Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve…
This paper investigates indoor point cloud semantic segmentation under scene-level annotation, which is less explored compared to methods relying on sparse point-level labels. In the absence of precise point-level labels, current methods…
We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images. We train a convolutional network to predict both the shape and the pose from a single image by minimizing the…
This paper presents a novel non-local part-aware deep neural network to denoise point clouds by exploring the inherent non-local self-similarity in 3D objects and scenes. Different from existing works that explore small local patches, we…
Exploiting past 3D LiDAR scans to predict future point clouds is a promising method for autonomous mobile systems to realize foresighted state estimation, collision avoidance, and planning. In this paper, we address the problem of…
A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…
Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…
Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often adapt an…
Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…
As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep…
To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object…
Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global…
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data,…
The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph…
Understanding and representing the structure of 3D objects in an unsupervised manner remains a core challenge in computer vision and graphics. Most existing unsupervised keypoint methods are not designed for unconditional generative…
3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…
In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a popular research…
A novel multi-level method for partial differential equations with uncertain parameters is proposed. The principle behind the method is that the error between grid levels in multi-level methods has a spatial structure that is by good…
Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…
Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on non-Euclidean domains is still a very active area of…