Related papers: RobustPointSet: A Dataset for Benchmarking Robustn…

This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are…

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…

End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants --…

Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…

Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud…

Point cloud anomaly detection under the anomaly-free setting poses significant challenges as it requires accurately capturing the features of 3D normal data to identify deviations indicative of anomalies. Current efforts focus on devising…

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…

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the…

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable…

Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface…

Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…

Data plays a crucial role in training learning-based methods for 3D point cloud registration. However, the real-world dataset is expensive to build, while rendering-based synthetic data suffers from domain gaps. In this work, we present…

Change detection from traditional \added{2D} optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud \added{from photogrammetry or LiDAR surveying} can fill this…

Understanding the spatial arrangement and nature of real-world objects is of paramount importance to many complex engineering tasks, including autonomous navigation. Deep learning has revolutionized state-of-the-art performance for tasks in…

Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them. However,…

Although supervised deep normal estimators have recently shown impressive results on synthetic benchmarks, their performance deteriorates significantly in real-world scenarios due to the domain gap between synthetic and real data. Building…

Due to scene complexity, sensor inaccuracies, and processing imprecision, point cloud corruption is inevitable. Over-reliance on input features is the root cause of DNN vulnerabilities. It remains unclear whether this issue exists in 3D…

We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods…

Diffusion-based models, widely used in text-to-image generation, have proven effective in 2D representation learning. Recently, this framework has been extended to 3D self-supervised learning by constructing a conditional point generator…