相关论文: NoiseTrans: Point Cloud Denoising with Transformer…

Reconstructing accurate implicit surface representations from point clouds remains a challenging task, particularly when data is captured using low-quality scanning devices. These point clouds often contain substantial noise, leading to…

Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising. Noise2Score3D learns the score function of the underlying point cloud distribution…

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by…

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering. Current approaches either try to optimize a non-data-driven surface representation to fit…

3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion, which have been widely applied in immersive telepresence, autonomous driving, surveillance, etc. However, point clouds acquired from…

Soft-tissue surgeries, such as tumor resections, are complicated by tissue deformations that can obscure the accurate location and shape of tissues. By representing tissue surfaces as point clouds and applying non-rigid point cloud…

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…

In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion.…

In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera…

The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying point clouds for achieving compact, clean, and uniform…

Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers, since they just…

Face recognition using 3D point clouds is gaining growing interest, while raw point clouds often contain a significant amount of noise due to imperfect sensors. In this paper, an end-to-end 3D face recognition on a noisy point cloud is…

We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input…

Visual imitation learning with 3D point clouds has advanced robotic manipulation by providing geometry-aware, appearance-invariant observations. However, point cloud-based policies remain highly sensitive to sensor noise, pose…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level.…

Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in…

Recent Transformer-based methods have achieved advanced performance in point cloud registration by utilizing advantages of the Transformer in order-invariance and modeling dependency to aggregate information. However, they still suffer from…