Related papers: ReconDreamer++: Harmonizing Generative and Reconst…

Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations and notable for their ease of data acquisition, have garnered considerable attention from both academic researchers and industry practitioners. The…

In this paper, we propose a novel approach, 3D-RecGAN++, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike existing work which typically requires…

Steering estimation is a critical task in autonomous driving, traditionally relying on 2D image-based models. In this work, we explore the advantages of incorporating 3D spatial information through hybrid architectures that combine 3D…

Learning-based 3D reconstruction using implicit neural representations has shown promising progress not only at the object level but also in more complicated scenes. In this paper, we propose Dynamic Plane Convolutional Occupancy Networks,…

Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier…

Purpose: To propose a novel deep learning-based method called RG-Net (reconstruction and generation network) for highly accelerated MR parametric mapping by undersampling k-space and reducing the acquired contrast number simultaneously.…

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

Since the resurgence of CNNs the robotic vision community has developed a range of algorithms that perform classification, semantic segmentation and structure prediction (depths, normals, surface curvature) using neural networks. While some…

Real-time open-vocabulary scene understanding is essential for efficient 3D perception in applications such as vision-language navigation, embodied intelligence, and augmented reality. However, existing methods suffer from imprecise…

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which…

This study explores the potential of graph neural networks (GNNs) to enhance semantic segmentation across diverse image modalities. We evaluate the effectiveness of a novel GNN-based U-Net architecture on three distinct datasets: PascalVOC,…

Real-time scene reconstruction from depth data inevitably suffers from occlusion, thus leading to incomplete 3D models. Partial reconstructions, in turn, limit the performance of algorithms that leverage them for applications in the context…

Implicit neural networks have emerged as a crucial technology in 3D surface reconstruction. To reconstruct continuous surfaces from discrete point clouds, encoding the input points into regular grid features (plane or volume) has been…

TGraphX presents a novel paradigm in deep learning by unifying convolutional neural networks (CNNs) with graph neural networks (GNNs) to enhance visual reasoning tasks. Traditional CNNs excel at extracting rich spatial features from images…

Transparent and reflective objects in everyday environments pose significant challenges for depth sensors due to their unique visual properties, such as specular reflections and light transmission. These characteristics often lead to…

Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies. Recently,…

In architecture and computer-aided design, wireframes (i.e., line-based models) are widely used as basic 3D models for design evaluation and fast design iterations. However, unlike a full design file, a wireframe model lacks critical…

Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…

Accurately segmenting roads is challenging due to substantial intra-class variations, indistinct inter-class distinctions, and occlusions caused by shadows, trees, and buildings. To address these challenges, attention to important texture…

Road network graphs provide critical information for autonomous-vehicle applications, such as drivable areas that can be used for motion planning algorithms. To find road network graphs, manually annotation is usually inefficient and…