Related papers: SHINE-Mapping: Large-Scale 3D Mapping Using Sparse…
Estimation of human shape and pose from a single image is a challenging task. It is an even more difficult problem to map the identified human shape onto a 3D human model. Existing methods map manually labelled human pixels in real 2D…
We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While…
The radio environment map (REM) visually displays the spectrum information over the geographical map and plays a significant role in monitoring, management, and security of spectrum resources.In this paper, we present an efficient 3D REM…
Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference. Variational inference has previously been employed to capture these distributions, however…
We present a novel mapping framework for robot navigation which features a multi-level querying system capable to obtain rapidly representations as diverse as a 3D voxel grid, a 2.5D height map and a 2D occupancy grid. These are inherently…
Traversing risky terrains with sparse footholds presents significant challenges for legged robots, requiring precise foot placement in safe areas. To acquire comprehensive exteroceptive information, prior studies have employed motion…
Despite the remarkable success of large large-scale neural networks, we still lack unified notation for thinking about and describing their representational spaces. We lack methods to reliably describe how their representations are…
3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This…
We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightforward interpretation of the reconstruction. We formulate…
Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers. This interplay, combined with their stabilizing effect on the gradient norms, enables them to train…
Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing Hyperspectral Image (HSI) typically involve learning mappings from a 2D…
Mapping and localization, preferably from a small number of observations, are fundamental tasks in robotics. We address these tasks by combining spatial structure (differentiable mapping) and end-to-end learning in a novel neural network…
Representing 3D objects and scenes with neural radiance fields has become very popular over the last years. Recently, surface-based representations have been proposed, that allow to reconstruct 3D objects from simple photographs. However,…
Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D…
Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based…
3D Gaussian splatting (3DGS) has recently demonstrated promising advancements in RGB-D online dense mapping. Nevertheless, existing methods excessively rely on per-pixel depth cues to perform map densification, which leads to significant…
A high-quality 3D reconstruction of a scene from a collection of 2D images can be achieved through offline/online mapping methods. In this paper, we explore active mapping from the perspective of implicit representations, which have…
The reconstruction of 3D cine-MRI is challenged by highly undersampled k-space data in each cine frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural…
Accurate and robust localization and mapping are essential components for most autonomous robots. In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact…
In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric…