Related papers: Adaptive Multi-step Refinement Network for Robust …
Place recognition is a fundamental component of robotics, and has seen tremendous improvements through the use of deep learning models in recent years. Networks can experience significant drops in performance when deployed in unseen or…
Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…
The analysis of software requirement specifications (SRS) using Natural Language Processing (NLP) methods has been an important study area in the software engineering field in recent years. Especially thanks to the advances brought by deep…
Point cloud registration plays a crucial role in various computer vision tasks, and usually demands the resolution of partial overlap registration in practice. Most existing methods perform a serial calculation of rotation and translation,…
Some robust point cloud registration approaches with controllable pose refinement magnitude, such as ICP and its variants, are commonly used to improve 6D pose estimation accuracy. However, the effectiveness of these methods gradually…
3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature…
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not…
Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during…
Point cloud registration is a fundamental problem in computer vision and robotics, involving the alignment of 3D point sets captured from varying viewpoints using depth sensors such as LiDAR or structured light. In modern robotic systems,…
Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great…
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level…
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…
Point cloud registration is a fundamental problem in many domains. Practically, the overlap between point clouds to be registered may be relatively small. Most unsupervised methods lack effective initial evaluation of overlap, leading to…
Spatial and channel re-calibration have become powerful concepts in computer vision. Their ability to capture long-range dependencies is especially useful for those networks that extract local features, such as CNNs. While re-calibration…
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.…
Three-dimensional (3D) point clouds are becoming more and more popular for representing 3D objects and scenes. Due to limited network bandwidth, efficient compression of 3D point clouds is crucial. To tackle this challenge, the Moving…
Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction. However,they usually suffer from two critical issues: (1)fixed upsampling rate after one-time…
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is…
Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made…