Related papers: Statistical Confidence Rescoring for Robust 3D Sce…

Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant…

We present a novel approach to reconstructing lightweight, CAD-based representations of scanned 3D environments from commodity RGB-D sensors. Our key idea is to jointly optimize for both CAD model alignments as well as layout estimations of…

Accurate prediction of 3D semantic occupancy from 2D visual images is vital in enabling autonomous agents to comprehend their surroundings for planning and navigation. State-of-the-art methods typically employ fully supervised approaches,…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their…

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

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…

Scene graphs provide structured semantic understanding beyond images. For downstream tasks, such as image retrieval, visual question answering, visual relationship detection, and even autonomous vehicle technology, scene graphs can not only…

We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular,…

The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks focus mainly on the geometric accuracy of the reconstructed…

Deep learning techniques have led to remarkable breakthroughs in the field of generic object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful…

Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…

Scene Text Recognition (STR) models have achieved high performance in recent years on benchmark datasets where text images are presented with minimal noise. Traditional STR recognition pipelines take a cropped image as sole input and…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previous approaches built a scene-dependent model that explicitly…

Learning to compose visual relationships from raw images in the form of scene graphs is a highly challenging task due to contextual dependencies, but it is essential in computer vision applications that depend on scene understanding.…

Generating realistic images of complex visual scenes becomes challenging when one wishes to control the structure of the generated images. Previous approaches showed that scenes with few entities can be controlled using scene graphs, but…

The vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, the presence of dynamic objects in the scene seriously affects the accuracy of the model…

Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…

Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…