Related papers: M$^3$CS: Multi-Target Masked Point Modeling with L…

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling…

Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for…

Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to the point cloud domain. Nevertheless, existing point cloud…

3D point clouds are often perturbed by noise due to the inherent limitation of acquisition equipments, which obstructs downstream tasks such as surface reconstruction, rendering and so on. Previous works mostly infer the displacement of…

As two fundamental representation modalities of 3D objects, 3D point clouds and multi-view 2D images record shape information from different domains of geometric structures and visual appearances. In the current deep learning era,…

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D…

With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning.…

Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D…

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the…

Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these features to generate pixel-level predictions. However, due…

We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with extremely sparse…

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…

Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

The pre-training architectures of large language models encompass various types, including autoencoding models, autoregressive models, and encoder-decoder models. We posit that any modality can potentially benefit from a large language…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. The range image is a dense representation of a large-scale outdoor point cloud, and segmentation…

This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input image and predicting the masked part by the unmasked part.…

Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation. In this work, a novel end-to-end deep…

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object…