Related papers: SimC3D: A Simple Contrastive 3D Pretraining Framew…

Most of 3D single object trackers (SOT) in point clouds follow the two-stream multi-stage 3D Siamese or motion tracking paradigms, which process the template and search area point clouds with two parallel branches, built on supervised point…

A main task in condensed-matter physics is to recognize, classify, and characterize phases of matter and the corresponding phase transitions, for which machine learning provides a new class of research tools due to the remarkable…

Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However, due to the unordered and non-uniform density characteristics of point clouds, it is non-trivial…

Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Thus far, this…

Most existing self-supervised learning (SSL) approaches for 3D point clouds are dominated by generative methods based on Masked Autoencoders (MAE). However, these generative methods have been proven to struggle to capture high-level…

2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. However,…

The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is an efficient way of exploiting the knowledge in unlabeled…

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…

The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications. As a result, constructing high-performance 3D convolutional neural networks from…

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…

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…

This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the…

Learning local descriptors is an important problem in computer vision. While there are many techniques for learning local patch descriptors for 2D images, recently efforts have been made for learning local descriptors for 3D points. The…

Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly…

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for…

Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve…

3D content inherently encompasses multi-modal characteristics and can be projected into different modalities (e.g., RGB images, RGBD, and point clouds). Each modality exhibits distinct advantages in 3D asset modeling: RGB images contain…

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…

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…

3D point cloud segmentation remains challenging for structureless and textureless regions. We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical…