Related papers: GPR-Net: Multi-view Layout Estimation via a Geomet…

We consider the robust Perspective-n-Point (PnP) problem using a hybrid approach that combines deep learning with model based algorithms. PnP is the problem of estimating the pose of a calibrated camera given a set of 3D points in the world…

We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame. We use DNNs to model the highly non-convex mapping…

Coarse room layout estimation provides important geometric cues for many downstream tasks. Current state-of-the-art methods are predominantly based on single views and often assume panoramic images. We introduce PixCuboid, an…

We propose a learning-based approach for novel view synthesis for multi-camera 360$^{\circ}$ panorama capture rigs. Previous work constructs RGBD panoramas from such data, allowing for view synthesis with small amounts of translation, but…

Absolute Pose Regression (APR) predicts 6D camera poses but lacks the adaptability to unknown environments without retraining, while Relative Pose Regression (RPR) generalizes better yet requires a large image retrieval database. Visual…

Appearance-based gaze estimation frequently relies on deep Convolutional Neural Networks (CNNs). These models are accurate, but computationally expensive and act as "black boxes", offering little interpretability. Geometric methods based on…

We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to…

Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) devices to detect subsurface objects (i.e., rebars, utility pipes) and reveal the underground scene. The two biggest challenges in GPR-based…

3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment.Recently,…

It is very challenging to reconstruct a high dynamic range (HDR) from a low dynamic range (LDR) image as an ill-posed problem. This paper proposes a luminance attentive network named LANet for HDR reconstruction from a single LDR image. Our…

We introduce Sky2Ground, a three-view dataset designed for varying altitude camera localization, correspondence learning, and reconstruction. The dataset combines structured synthetic imagery with real, in-the-wild images, providing both…

Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach has been to use standard convolutional networks to predict…

The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images. In contrast, we are the first to address this challenge by using objectness regions to guide the pose estimation…

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…

Recently, learning-based multi-view stereo methods have achieved promising results. However, they all overlook the visibility difference among different views, which leads to an indiscriminate multi-view similarity definition and greatly…

Full 3D estimation of human pose from a single image remains a challenging task despite many recent advances. In this paper, we explore the hypothesis that strong prior information about scene geometry can be used to improve pose estimation…

Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud…

Generating immersive 360{\deg} indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for…

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is…

In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric…