Related papers: Attention-based Transformation from Latent Feature…
Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution operations or attention mechanisms, exploiting geometric…
Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching…
Vision transformers have shown outstanding performance in image generation, yet their adoption in fluid dynamics remains limited. We introduce the Latent Attention on Masked Patches (LAMP) model, an interpretable regression-based modified…
We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…
We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as…
Point cloud completion seeks to recover geometrically consistent shapes from partial or sparse 3D observations. Although recent methods have achieved reasonable global shape reconstruction, they often rely on Euclidean proximity and…
The continual improvement of 3D sensors has driven the development of algorithms to perform point cloud analysis. In fact, techniques for point cloud classification and segmentation have in recent years achieved incredible performance…
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale registration methods are rarely explored. Challenges mainly arise from the huge point number, complex distribution, and…
In this paper, we introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion without requiring iterative spatial propagations. Specifically, we first enhance a baseline convolutional depth…
The universality of the point cloud format enables many 3D applications, making the compression of point clouds a critical phase in practice. Sampled as discrete 3D points, a point cloud approximates 2D surface(s) embedded in 3D with a…
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on…
The increasing demand for accurate representations of 3D scenes, combined with immersive technologies has led point clouds to extensive popularity. However, quality point clouds require a large amount of data and therefore the need for…
This paper addresses the challenge of perceiving complete object shapes through visual perception. While prior studies have demonstrated encouraging outcomes in segmenting the visible parts of objects within a scene, amodal segmentation, in…
In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates. While existing methods incorporate convolutional priors with occasional…
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene flow is estimated from dense/regular RGB video frames. With the…
Point Transformers are near state-of-the-art models for classification, segmentation, and detection tasks on Point Cloud data. They utilize a self attention based mechanism to model large range spatial dependencies between multiple point…
Point clouds are a basic data type that is increasingly of interest as 3D content becomes more ubiquitous. Applications using point clouds include virtual, augmented, and mixed reality and autonomous driving. We propose a more efficient…
Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from…
We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes the occupancy field of the shape and respects the inherent…