Related papers: NeuralPCI: Spatio-temporal Neural Field for 3D Poi…

The rise of large-scale models has catalyzed in-context learning as a powerful approach for multitasking, particularly in natural language and image processing. However, its application to 3D point cloud tasks has been largely unexplored.…

Point cloud scene flow estimation is fundamental to long-term and fine-grained 3D motion analysis. However, existing methods are typically limited to pairwise settings and struggle to maintain temporal consistency over long sequences as…

Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are proposed to synthesize realistic images from 2D input. In this…

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how…

Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint…

3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving. Despite its wide-ranging use, this task remains challenging due to the significant appearance variation caused by…

We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the…

Recent advancements in machine learning, particularly through deep learning architectures like PointNet, have transformed the processing of three-dimensional (3D) point clouds, significantly improving 3D object classification and…

Artificial intelligence (AI) has revolutionized software development, shifting from task-specific codes (Software 1.0) to neural network-based approaches (Software 2.0). However, applying this transition in engineering software presents…

We address the challenge of novel view synthesis from only two input images under large viewpoint changes. Existing regression-based methods lack the capacity to reconstruct unseen regions, while camera-guided diffusion models often deviate…

3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc. They are often perturbed by noise or suffer from low density,…

The task of Novel Class Discovery (NCD) in semantic segmentation entails training a model able to accurately segment unlabelled (novel) classes, relying on the available supervision from annotated (base) classes. Although extensively…

Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this…

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal…

Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration performance can be enhanced if these connections be harnessed…

Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel…

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between…

Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks. Among them, time-series modeling with neural controlled differential equations…

Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle…

Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected by illumination and season…