Related papers: Geometry-Aware Self-Training for Unsupervised Doma…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Point cloud registration is a key task in many computational fields. Previous correspondence matching based methods require the inputs to have distinctive geometric structures to fit a 3D rigid transformation according to point-wise sparse…

Semantic segmentation on point clouds is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with…

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this…

In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source…

In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an…

LiDAR-based 3D object detection is an indispensable task in advanced autonomous driving systems. Though impressive detection results have been achieved by superior 3D detectors, they suffer from significant performance degeneration when…

3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor…

We propose a unified point cloud video self-supervised learning framework for object-centric and scene-centric data. Previous methods commonly conduct representation learning at the clip or frame level and cannot well capture fine-grained…

The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

With recent success of deep learning in 2D visual recognition, deep learning-based 3D point cloud analysis has received increasing attention from the community, especially due to the rapid development of autonomous driving technologies.…

Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target…

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,…

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance…

The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple…

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the…

Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on…