Localizing 3D cuboids in single-view images

By Jianxiong Xiao, Bryan C. Russell, Antonio Torralba. 2012

114 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Category-specific object reconstruction from a single image (2014, methodology): “Polyhedral models [18, 40], which trace back to the early work of Roberts [29], and CAD models [25, 31] provide crude approximations of shape and given a set of point correspondences can be quite effective for determining instance viewpoints.”
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (2016, methodology): “Parametric models, such as volumetric models [24], cuboids [48], joint cuboid and room layout [38], and support surfaces (in RGB-D) [13] have been proposed.”
IM2CAD (2016, background): “More recently, researchers have moved beyond walls, and toward approximating furniture in the room using cuboids [46, 49, 8, 14, 29, 38].”
Data-Driven 3D Primitives for Single Image Understanding (2013, unknown): “The most commonly used primitives include oriented 3D surfaces [14, 19, 23, 31] represented as segments in the image, or volumetric primitives such as blocks [11] and cuboids [18, 33].”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
Unfolding an Indoor Origami World (2014, background): “Recent work has aimed at overcoming this by finding volumetric primitives inside scenes, conventionally cuboids [8,22,36,31], and in simple scenes”
Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines (2013, background): “[13, 29] contain 3D bounding box annotations for cuboid-like objects in RGBD images.”
Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models (2014, background): “Others have explored simplified 3D cuboid models for reasoning about outdoor scenes [18] or detecting and estimating pose for box-like objects such as printers, beds or sofas [15, 39], often using simplifying 3D box-layout constraints for indoor scenes [7, 11].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Reasoning from Blocks to Stability (background): “Xiao et al. [13] detect 3D cuboids with arbitrary orientations solely in RGB images, Bleyer et al. [14] show box fitting for improved stereo, and Jiang et al. [15] propose a linear programming for fitting cuboids in depth images.”
Inverse Graphics with Probabilistic CAD Models (2014, background): “Generative models for natural images have instead either focused on 2D problems [17], considered only low-dimensional latent scenes comprised of simple shapes[18, 9], or made heavy use of temporal continuity [21].”
FPM: Fine Pose Parts-Based Model with 3D CAD Models (2014, background): “Various recent works have tackled the problem of object-level pose estimation [37,21,11].”
Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients (2016, methodology): “Several methods fit cuboid models to RGB or RGB-D data [17, 16, 40] but do not have any semantic, high-level scene understanding.”
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views (2015, methodology): “Furthermore, simplified or parametric geometric models have been used for category recognition/detection [15, 20, 24, 42, 58, 60].”
Scene Parsing by Integrating Function, Geometry and Appearance Models (2013, background): “[24], Hejrati and Ramanan [14], Xiang and Savarese [22], Pepik et al.”
CubeSLAM: Monocular 3-D Object SLAM (2018, methodology): “This is similar to the Chamfer distance [10].”
Robust real-time visual odometry for dense RGB-D mapping (2013, background): “[24] notes that an affordance can be described by the three interdependent entities of action, object, and effect.”