Related papers: Collect-and-Distribute Transformer for 3D Point Cl…
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of…
As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because…
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware…
Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we…
Common deep learning models for 3D environment perception often use pillarization/voxelization methods to convert point cloud data into pillars/voxels and then process it with a 2D/3D convolutional neural network (CNN). The pioneer work…
This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set"…
Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation,…
3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context…
Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…
This paper proposes a 4D backbone for long-term point cloud video understanding. A typical way to capture spatial-temporal context is using 4Dconv or transformer without hierarchy. However, those methods are neither effective nor efficient…
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…
To apply transformer-based models to point cloud understanding, many previous works modify the architecture of transformers by using, e.g., local attention and down-sampling. Although they have achieved promising results, earlier works on…
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this paper, we introduce a new…
Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…
As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point…
Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…
Recent transformer-based approaches have demonstrated excellent performance in 3D human pose estimation. However, they have a holistic view and by encoding global relationships between all the joints, they do not capture the local…