3D Box Proposals from a Single Monocular Image of an Indoor Scene

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Differentiable rendering (DR) is an emerging field that facilitates the calculation and propagation of gradients of 3D objects through images. In contrast to deep neural networks (DNNs), which generally lack the understanding of 3D objects that form the im ...

Current post-earthquake damage assessment methodologies are not only time-consuming but also subjective in nature and difficult to document. Recent advancements in artificial intelligence and technological devices make it possible to accomplish this task a ...

Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and fine-grained pre ...

Millimeter wave (mmWave) radars are becoming a more popular sensing modality in self-driving cars due to their favorable characteristics in adverse weather. Yet, they currently lack sufficient spatial resolution for semantic scene understanding. In this pa ...

Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to the simpli ...

An assembly refers to a collection of parts joined together to achieve a specific form and/or functionality. Designing assemblies is a non-trivial task as a slight local modification on a part's geometry or its joining method could have a global impact on ...

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

Existing depth sensing techniques have many shortcomings in terms of resolution, completeness, and accuracy. The performance of 3-D broadcasting systems is therefore limited by the challenges of capturing high-resolution depth data. In this paper, we prese ...

We consider an adaptive isogeometric method (AIGM) based on (truncated) hierarchical B-splines and present the study of its numerical properties. By following [10, 12, 11], optimal convergence rates of the AIGM can be proved when suitable approximation cla ...

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task [ ...

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, a ...

A depth image provides partial geometric information of a 3D scene, namely the shapes of physical objects as observed from a particular viewpoint. This information is important when synthesizing images of different virtual camera viewpoints via depth-image ...

Color plus depth format allows building 3D representations of scenes within which the users can freely navigate by changing their viewpoints. In this paper we present a framework for view synthesis when the user requests an arbitrary viewpoint that is clos ...

In multiview systems, color plus depth format builds 3D representations of scenes within which the users can freely navigate by changing their viewpoints. In this paper we present a framework for view synthesis when the user requests an arbitrary viewpoint ...

In free viewpoint video systems, where a user has the freedom to select a virtual view from which an observation image of the 3D scene is rendered, the scene is commonly represented by texture and depth images from multiple nearby viewpoints. In such repre ...

Capturing and processing human geometry, appearance, and motion is at the core of computer graphics, computer vision, and human-computer interaction. The high complexity of human geometry and motion dynamics, and the high sensitivity of the human visual sy ...

A novel methodology consisting of three hierarchical levels is proposed for the detection phase of contact mechanics simulations. The top level of the hierarchy uses kinematic information from the objects involved in the simulation to determine approximate ...

Compression of dynamic 3D geometry obtained from depth sensors is challenging, because noise and temporal inconsistency inherent in acquisition of depth data means there is no one-to-one correspondence between sets of 3D points in consecutive time instants ...

3D Box Proposals from a Single Monocular Image of an Indoor Scene

Chat with Graph Search

Inverse Rendering for PET Image Reconstruction

Automated post-earthquake damage assessment of stone masonry buildings integrating machine learning, computer vision, and physics-based modeling

Pedestrian 3D Bounding Box Prediction

Radatron: Accurate Detection Using Multi-resolution Cascaded MIMO Radar

Learning to Represent and Reconstruct 3D Deformable Objects

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

State of the Art on Computational Design of Assemblies with Rigid Parts

Neural Scene Decomposition for Multi-Person Motion Capture

Global Auto-regressive Depth Recovery via Iterative Non-local Filtering

Adaptive Isogeometric Methods With Hierarchical Splines: An Overview

Real-Time Seamless Single Shot 6D Object Pose Prediction

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Object Shape Approximation and Contour Adaptive Depth Image Coding for Virtual View Synthesis

Graph-Based Inpainting of Disocclusion Holes for Zooming in 3D Scenes

Graph-Based Interpolation for Zooming in 3D Scenes

Encoder-Driven Inpainting Strategy in Multiview Video Compression

Realtime Face Tracking and Animation

A hierarchical detection framework for computational contact mechanics

3D Geometry Representation using Multiview Coding of Image Tiles