Bayesian geometric modeling of indoor scenes

By Luca Del Pero, Joshua Bowdish, Daniel Fried, Bonnie Kermgard, Emily Hartley, Kobus Barnard. 2012

138 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

On the Binding Problem in Artificial Neural Networks (2020, background): “The results that can be obtained by incorporating domain-specific knowledge are impressive (Zhao and Zhu, 2011; Del Pero et al., 2012, 2013; Tu et al., 2005; Tu and Zhu, 2002).”
Multi-Object Representation Learning with Iterative Variational Inference (2019, background): “, 2015) or 3D indoor scene rendering (Pero et al., 2012), have produced appealing results, but require carefully engineered generative models, which are typically not fully learned from data.”
Unsupervised Learning of 3D Structure from Images (2016, methodology): “In our experiments, context is either 1) nothing, 2) an object class label, or 3) one or more views of the scene from different cameras.”
Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs (2013, background): “Generative models for a range of image parsing tasks are also being explored [17, 4, 18, 22, 20].”
Scene Parsing by Integrating Function, Geometry and Appearance Models (2013, methodology): “2, we also test our algorithm on the UCB dataset and the UIUC dataset together with five state-of-the-art algorithms: Hedau 2009 [12], Wang 2010 [21], Lee 2010 [16], Del Pero 2011 [4] and Del Pero 2012 [3].”
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].”
3DNN: 3D Nearest Neighbor (2014, methodology): “3 for an overview of this process.”
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].”
The informed sampler: A discriminative approach to Bayesian inference in generative computer vision models (2014, background): “This includes applications such as indoor scene understanding (Del Pero et al., 2012), human pose estimation (Lee and Cohen, 2004), hand pose estimation (de La Gorce et al., 2008) and many more.”
Efficient Exact Inference for 3D Indoor Scene Understanding (2012, methodology): “Also note that the approach proposed in [24] requires about 12 minutes per image in the layout dataset.”
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].”
IM2CAD (2016, background): “Lee et al. [22] 24.70 Hedau et al. [15] 21.20 Del Pero et al. [29] 16.30 Gupta et al. [14] 16.20 Zhao et al. [50] 14.50 Schwing et al. [39] 13.59 Ramalingam et al. [31] 13.34 Mallya et al. [27] 12.83 Dasgupta et al. [9] 9.73 Ren et al. [33] 8.67 IM2CAD 10.15 Table 1: Room layout pixel…”
Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects (2016, background): “In computer vision, size information manually extracted from furniture catalogs, has shown to be effective in indoor scenes understanding and reconstruction (Pero et al. 2012).”
Gen: a general-purpose probabilistic programming system with programmable inference (2019, methodology): “Then, object parameters are estimated from an observed image using posterior inference in the generative model [14, 39].”
Localizing 3D cuboids in single-view images (2012, background): “Compared with recent approaches that detect cuboids by reasoning about the shape of the entire scene [9, 11, 12, 17, 19, 29], one of the key differences is that we detect cuboids directly without consideration of the global scene geometry.”
Deep Generative Vision as Approximate Bayesian Computation (2014, background): “Moreover, generative models for natural images have been widely explored by a variety of analysis-by-synthesis approaches [19, 5, 24, 22].”
Understanding Bayesian Rooms Using Composite 3D Object Models (2013, methodology): “∝ p(D|θ)p(θ) , (1) where D are features detected on the image plane and p(θ) is the prior distribution over model parameters.”