Efficient Exact Inference for 3D Indoor Scene Understanding

By Alexander Gerhard Schwing, Raquel Urtasun. 2012

123 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

3D Shape Induction from 2D Views of Multiple Objects (2016, methodology): “Recognition-based methods have been used to estimate geometry of out-door scenes [14, 26], indoor environments [9, 27], and objects [1, 25].”
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (2016, background): “Prior work has sought to recover the overall global shape of the room by fitting a global parametric 3D box [17, 39] or recovering informative edge maps [29] that align to the shape of the room, typically based on Manhattan world constraints [8, 21].”
3DNN: 3D Nearest Neighbor (2014, background): “(2011),Schwing and Urtasun (2012) or any other algorithm could easily be incorporated to improve robustness.”
Learning to Search in Branch and Bound Algorithms (2014, methodology): “In applied domains, it has been applied to the “inference” stage of structured prediction problems (e.g., dependency parsing [4, 5], scene understanding [6], ancestral sequence reconstruction [7]).”
Discrete-Continuous Depth Estimation from a Single Image (2014, methodology): “, box models) have proven effective to estimate the layout of a room [9, 17, 27].”
Designing deep networks for surface normal estimation (2014, methodology): “However, decades of research have shown that the output space of this task is governed by powerful physical constraints and researchers have exploited these constraints from the very beginning of computer vision [27] through the line-labeling era [17, 2, 19] all the way to recent investigations [14,”
Understanding Indoor Scenes Using 3D Geometric Phrases (2013, methodology): “Several methods attempted to specifically solve indoor layout estimation [12, 13, 27, 30, 22, 26, 25].”
Data-Driven 3D Primitives for Single Image Understanding (2013, methodology): “, by a learned model such as in [23], a hierarchical segmentation [14], physical and volumetric relationships [18], recognizing primitives as parts of semantic objects [31], or assuming a Manhattan world and low-parameter room layout model [13, 35, 26].”
Unfolding an Indoor Origami World (2014, unknown): “developing constrained models for the prediction of room layout [10] as well as features [6,23,27] and effective methods for inference [4,22,31,32].”
Blending Learning and Inference in Conditional Random Fields (2016, background): “Considering indoor scene understanding (Schwing et al., 2012a; Schwing and Urtasun, 2012; Lin et al., 2013) each wall or a 3D object in the room is represented by a subsets of variables and our learning algorithm estimates the position of these objects while maximizing likelihood of these subsets…”
Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors (2013, background): “Indoor scene understanding approaches have taken advantage of the Manhattan world properties of rooms and frame the layout estimation task as the prediction of a 3D cuboid aligned with the three main dominant orientations [10, 11, 18, 22, 23, 16, 29].”
Omnidirectional 3D reconstruction in augmented Manhattan worlds (2014, background): “1(b), many urban scenes closely follow this assumption and also indoor scenes are often composed of mainly horizontal or vertical surfaces [8], [9].”
Single Image 3D without a Single 3D Image (2015, methodology): “At test time, this local mapping is used on a single image to infer the 3D labels; in other works, it is again presumed that there is such regularity that one can impose even more top-down constraints, such as the Manhattan-world assumption [8], an indoor box model [20, 35], or others [27, 6, 5, 17,”