Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry

By Varsha Hedau, Derek Hoiem, D.A. Forsyth. 2010

294 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Voting for Voting in Online Point Cloud Object Detection (2015, background): “A body of work in monocular object detection with 3D pose estimation [9, 7] also characterises objects by 3D bounding boxes identified by sliding a window in 3D.”
Deep convolutional neural fields for depth estimation from a single image (2014, background): “, box models, to infer the spatial layout of a room [2,3] or outdoor scenes [4].”
Picture: A probabilistic programming language for scene perception (2015, methodology): “Procedural graphics techniques [2, 10] would support far more complex object and scene models [50, 14, 7, 15].”
Bayesian geometric modeling of indoor scenes (2012, background): “Specifically, there has been much interest in estimating the 3D layout of rooms from single images (position of walls, floor and ceiling), as this provides crucial information on the scene geometric context, which allows to reason about objects [6, 9] and human activities [4].”
FPM: Fine Pose Parts-Based Model with 3D CAD Models (2014, background): “There have also been several works [15,18,23,22,32,38] addressing the problem of estimating the structure of a scene from a single image.”
Superparsing (2010, background): “(2009) infer the “box” of a room and then leverage the geometry of that box to align object detectors to the scene (Hedau and Hoiem 2010).”
Understanding Bayesian Rooms Using Composite 3D Object Models (2013, methodology): “We also designed specific data-driven inference mechanisms for each part that are shared by all objects containing that part, which helps make inference transparent to the modeler.”
Semantic structure from motion with points, regions, and objects (2012, background): “Among these works (e.g. [12] [15] [11] [25] [10] [20] [6] [13]), most assume that only a single image is available, whereas a handful of them model this problem with multiple images.”
3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model (2012, methodology): “These differences are important, as our approach outperforms [2] by a significant margin.”
Indoor scene segmentation using a structured light sensor (2011, background): “[19] recovers the 3D structure of the room from a single image, which then provides context for recognition.”
Scene Understanding by Reasoning Stability and Safety (2015, background): “There has also been interesting work in constructing 3D scene layouts from 2D images for indoor scenes, such as Zhao and Zhu (2011), Lee et al. (2009) (2010), and Hedau et al. (2010).”
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects (2014, background): “In recent literature, there has been a strong movement away from considering objects in isolation, towards reasoning jointly about entire scenes, aiding recognition in tasks like scene understanding [20, 34, 19, 18] and object tracking [10, 4] by exploiting contextual relationships between objects a”