Creating consistent scene graphs using a probabilistic grammar

By Niloy J. Mitra. 2014

82 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

ShapeNet: An Information-Rich 3D Model Repository (2015, background): “contains around 1,800 3D models grouped into 90 categories, but has no annotations beyond category labels. Other commonly-used datasets contain segmentations [2], correspondences [13,12], hierarchies [19], symmetries [11], salient features [3], semantic segmentations and labels [36], alignments of 3”
Discovering objects and their relations from entangled scene representations (2017, methodology): “In graphics, a number of approaches have been used to capture contextual scene structure, such as energy models (Yu et al., 2011), graphical and mixture models (Fisher et al., 2011; 2012), stochastic grammars (Liu et al., 2014), and probabilistic programs (Talton et al., 2012; Yeh et al., 2012).”
Data-driven structural priors for shape completion (2015, background): “, groupings of objects and parts reduce complexity of the representation [Liu et al. 2014]), and generalizing the symmetry term to a regularization term that favors repetitions on different levels of the hierarchy (i.”
Learning a Generative Model for Multi‐Step Human‐Object Interactions from Videos (2019, methodology): “In order to obtain these, we ﬁrst use Faster R-CNN [RHGS15] pre-trained on the Microsoft COCO dataset [LMB ∗ 14] to ﬁnd candidate bounding boxes with corresponding object category labels in every frame.”
Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (2020, background): “A line of works use probabilistic grammar to parse scenes [28, 53] or control scene synthesis [15].”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, unknown): “Note that [48] exhibits nearly the same performance on both our dataset and the NYU v2 Dataset, which indicates that our synthetic scenes are suitable for algorithm evaluation.”
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding (2016, background): “e context is usually manually deﬁned as a unary term on a single object, pairwise term between a pair of objects to satisfy certain functionality [23,46], or a more complicated hierarchy architecture [6,24,49]. The learned context models are usually applied on a large set of object hypotheses genera”
Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation (2017, background): “This track receives long-lasting endorsement due to its interpretability and effectiveness in modeling diverse tasks (Liu et al. 2014; Xu et al. 2016; 2017).”