Related papers: Deep-JGAC: End-to-End Deep Joint Geometry and Attr…
While point cloud-based applications are gaining traction due to their ability to provide rich and immersive experiences, they critically need efficient coding solutions due to the large volume of data involved, often many millions of…
Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge…
Recent advances in deep learning-based joint source-channel coding (deepJSCC) have substantially improved communication performance, but their high computational cost hinders practical deployment. Moreover, certain applications require the…
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…
3D sensing and content capture have made significant progress in recent years and the MPEG standardization organization is launching a new project on immersive media with point cloud compression (PCC) as one key corner stone. In this work,…
Existing AI-based point cloud compression methods struggle with dependence on specific training data distributions, which limits their real-world deployment. Implicit Neural Representation (INR) methods solve the above problem by encoding…
Generalization remains a critical challenge in deep learning-based point cloud geometry compression. While existing methods perform well on standard benchmarks, their performance collapses in real-world scenarios due to two fundamental…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
We propose an intra frame predictive strategy for compression of 3D point cloud attributes. Our approach is integrated with the region adaptive graph Fourier transform (RAGFT), a multi-resolution transform formed by a composition of…
Machine vision systems, which can efficiently manage extensive visual perception tasks, are becoming increasingly popular in industrial production and daily life. Due to the challenge of simultaneously obtaining accurate depth and texture…
We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe the underlying geometry of Computer…
Voxel-based methods are among the most efficient for point cloud geometry compression, particularly with dense point clouds. However, they face limitations due to a restricted receptive field, especially when handling high-bit depth point…
Point clouds or depth images captured by current RGB-D cameras often suffer from low resolution, rendering them insufficient for applications such as 3D reconstruction and robots. Existing point cloud super-resolution (PCSR) methods are…
Although convolutional representation of multiscale sparse tensor demonstrated its superior efficiency to accurately model the occupancy probability for the compression of geometry component of dense object point clouds, its capacity for…
Stable diffusion networks have emerged as a groundbreaking development for their ability to produce realistic and detailed visual content. This characteristic renders them ideal decoders, capable of producing high-quality and aesthetically…
This paper addresses the problem of compression of 3D point cloud sequences that are characterized by moving 3D positions and color attributes. As temporally successive point cloud frames are similar, motion estimation is key to effective…
The joint source-channel coding (JSCC) framework leverages deep learning to learn from data the best codes for source and channel coding. When the output signal, rather than being binary, is directly mapped onto the IQ domain…
We propose DepthTCM, a physics-aware end-to-end framework for depth map compression. In our framework of DepthTCM, the high-bit depth map is first converted to a conventional 3-channel image representation losslessly using a method inspired…
Point cloud registration has seen significant advancements with the application of deep learning techniques. However, existing approaches often overlook the potential of integrating radiometric information from RGB images. This limitation…
Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of…