Related papers: Learning Scene Flow in 3D Point Clouds with Noisy …
Learning signed distance functions (SDFs) from 3D point clouds is an important task in 3D computer vision. However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning…
3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To alleviate the annotation cost, we propose the first…
Monocular 3D object detection is a challenging task in the self-driving and computer vision community. As a common practice, most previous works use manually annotated 3D box labels, where the annotating process is expensive. In this paper,…
Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current…
Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous…
In this work, we pioneer Semantic Flow, a neural semantic representation of dynamic scenes from monocular videos. In contrast to previous NeRF methods that reconstruct dynamic scenes from the colors and volume densities of individual…
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…
Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point…
3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…
Semantic understanding of 3D point clouds is important for various robotics applications. Given that point-wise semantic annotation is expensive, in this paper, we address the challenge of learning models with extremely sparse labels. The…
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…
Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…
LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…
Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of…
Existing LiDAR-based 3D object detectors typically rely on manually annotated labels for training to achieve good performance. However, obtaining high-quality 3D labels is time-consuming and labor-intensive. To address this issue, recent…
Point cloud segmentation with scene-level annotations is a promising but challenging task. Currently, the most popular way is to employ the class activation map (CAM) to locate discriminative regions and then generate point-level pseudo…
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…
Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D…
3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in…
We present a new point-based approach for modeling the appearance of real scenes. The approach uses a raw point cloud as the geometric representation of a scene, and augments each point with a learnable neural descriptor that encodes local…