Related papers: Position-aware Guided Point Cloud Completion with …
3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing point-based methods are challenging to reach the speed…
Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
Discrete point cloud objects lack sufficient shape descriptors of 3D geometries. In this paper, we present a novel method for aggregating hypothetical curves in point clouds. Sequences of connected points (curves) are initially grouped by…
As 3D scanning solutions become increasingly popular, several deep learning setups have been developed geared towards that task of scan completion, i.e., plausibly filling in regions there were missed in the raw scans. These methods,…
LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a…
3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically deficient LiDAR point clouds. While motion paradigm…
Place recognition is an important technique for autonomous cars to achieve full autonomy since it can provide an initial guess to online localization algorithms. Although current methods based on images or point clouds have achieved…
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…
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…
Completing an unordered partial point cloud is a challenging task. Existing approaches that rely on decoding a latent feature to recover the complete shape, often lead to the completed point cloud being over-smoothing, losing details, and…
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…
Learning discriminative shape representation directly on point clouds is still challenging in 3D shape analysis and understanding. Recent studies usually involve three steps: first splitting a point cloud into some local regions, then…
Large-scale colored point clouds have many advantages in navigation or scene display. Relying on cameras and LiDARs, which are now widely used in reconstruction tasks, it is possible to obtain such colored point clouds. However, the…
Category-level articulated object pose estimation focuses on the pose estimation of unknown articulated objects within known categories. Despite its significance, this task remains challenging due to the varying shapes and poses of objects,…
Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios. Recent works have explored vision-language models (VLMs) as a promising alternative,…
Point cloud surface reconstruction has improved in accuracy with advances in deep learning, enabling applications such as infrastructure inspection. Recent approaches that reconstruct from small local regions rather than entire point clouds…
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and…
This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the…