Scene Parsing by Integrating Function, Geometry and Appearance Models

By Yibiao Zhao, Song-Chun Zhu. 2013

153 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Continuous Scene Representations for Embodied AI (2022, background): “Towards building such representations, scene graphs [2, 29, 65] are a candidate as they provide a compact and explicit description of a scene.”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, methodology): “It has been employed in computer vision to model objects [6], scenes [7], [8] and events [9], [10].”
Scene Graph Generation by Iterative Message Passing (2017, background): “As indicated by a series of previous works [26, 34, 41], one crucial step towards a deeper understanding of visual scenes is building a structured representation that captures objects and their semantic relationships.”
Semantically-enriched 3D models for common-sense knowledge (2015, background): “The impact of gravity can be felt continuously by people and influences the structure of objects in the world.”
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.”
Unfolding an Indoor Origami World (2014, background): “Some include conditional random field (CRF)-based smoothness reasoning [26], cuboidal room layout [10] and volumetric representation of objects [8,22], 3D objects [35], and groups of objects [1,40,41].”
Designing deep networks for surface normal estimation (2014, background): “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,”
Affordances from Human Videos as a Versatile Representation for Robotics (2023, unknown): “Given a scene, one can predict interactions using geometrybased rules for objects via 3D scene understanding [43, 78, 79, 134], estimating 3D physical attributes [8, 26, 41, 137] or through segmentation models trained on semantic interactions [102, 104], and thus require specialized datasets.”
Creating consistent scene graphs using a probabilistic grammar (2014, methodology): “CR Categories: I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling—Geometric algorithms Keywords: scene understanding, scene collections Links: DL PDF WEB DATA CODE”
Image retrieval using scene graphs (2015, result): “Parse graphs obtained in scene parsing [70, 65] are typically the result of applying a grammar designed for a particular domain (such as indoor scenes [70]), in contrast to our generic scene graphs.”
Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense (2019, background): “(iii) Joint estimation of the room layout and 3D objects with contexts [40, 54, 7, 52, 62].”
Building a Large-scale Multimodal Knowledge Base for Visual Question Answering (2015, background): “Another is to understand and recognize the image contents with more details or interconnected context, such as image recognition based on context [4, 24, 36] and joint learning and recognition of physical properties, functions, and appearance [34, 39, 42].”
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera (2019, background): “Grammars that combine geometry, affordance and appearance have been used toward holistic scene parsing in images, where information about the scene and objects is captured in a hierarchical tree structure [11, 48, 21, 19].”
3DNN: 3D Nearest Neighbor (2014, methodology): “Additionally, the vision community has begun utilizing this data to learn about the sizes, shapes and affordances of objects (Grabner et al. 2011; Zhao and Zhu 2013).”
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects (2014, methodology): “Recently, more fine-grained, geometric representations have been successfully applied to the understanding of indoor scenes [7, 9, 38], where a box-like room layout is populated with furniture objects.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “As the fidelity and complexity of the simulation increased, Zhu et al. [233] were able to infer the forces impacting a seated human body, using a finite element method (FEM) to generate a mesh estimating the force on various body parts; Fig.”
Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries (2015, background): “Similarly, the family of And-Or graph models [47, 56] focus on parsing images and videos into a hierarchical structure.”
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,”