Related papers: Occlusion-aware Text-Image-Point Cloud Pretraining…

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity…

Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transformer-based models to encode global features and facilitate…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel…

State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training have demonstrated potential in learning 3D representations by…

The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a dividing-and-conquering strategy, which involves: 1)…

The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects effectively. In this paper, we integrate two prevalent…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable…

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…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging. Many recent studies on point cloud pre-training, however, have overlooked the issue of incompleteness, where…

Point-cloud data collected in real-world applications are often incomplete. Data is typically missing due to objects being observed from partial viewpoints, which only capture a specific perspective or angle. Additionally, data can be…

The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as…

Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning. The pre-trained models with high representation ability and transferability achieve a great success and dominate many downstream tasks in…

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data. To work well in the real world, the policy needs to see many instances of…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution. However, the contexts gathered by the previous voxel-based methods decrease when handling sparse point clouds. To address this…

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…

Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road…