Related papers: Malleable 2.5D Convolution: Learning Receptive Fie…

Image translation with convolutional autoencoders has recently been used as an approach to multimodal change detection in bitemporal satellite images. A main challenge is the alignment of the code spaces by reducing the contribution of…

We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construction is the notion of directional functions defined on the…

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object…

Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention…

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect. The standard convolution characterises feature correspondences indistinguishably among 3D points, presenting an intrinsic…

Scene understanding for autonomous vehicles is a challenging computer vision task, with recent advances in convolutional neural networks (CNNs) achieving results that notably surpass prior traditional feature driven approaches. However,…

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method…

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations…

Differentiable rendering is a technique to connect 3D scenes with corresponding 2D images. Since it is differentiable, processes during image formation can be learned. Previous approaches to differentiable rendering focus on mesh-based…

With the advent of deep learning, estimating depth from a single RGB image has recently received a lot of attention, being capable of empowering many different applications ranging from path planning for robotics to computational…

Recently, various convolutions based on continuous or discrete kernels for point cloud processing have been widely studied, and achieve impressive performance in many applications, such as shape classification, scene segmentation and so on.…

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models…

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to…

A key challenge in video enhancement and action recognition is to fuse useful information from neighboring frames. Recent works suggest establishing accurate correspondences between neighboring frames before fusing temporal information.…

In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and…

Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it…

We present a novel surface convolution operator acting on vector fields that is based on a simple observation: instead of combining neighboring features with respect to a single coordinate parameterization defined at a given point, we have…

Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and…

In this paper, we propose to exploit the rich hierarchical features of deep convolutional neural networks to improve the accuracy and robustness of visual tracking. Deep neural networks trained on object recognition datasets consist of…