Make it home: automatic optimization of furniture arrangement

By Lap-Fai Craig Yu, Sai-Kit Yeung, Chi-Keung Tang, Demetri Terzopoulos, Tony F. Chan, Stanley J. Osher. ACM Transactions on Graphics, 2011

468 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

View Paper: https://www.semanticscholar.org/paper/f7232f37fedcc592f571833e2ddf8eba4746b7e2

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 Graphics and Computer-Aided Design

In Geology

Citations in the corpus

Understanding RealWorld Indoor Scenes with Synthetic Data (2015, methodology): “Additionally, we generate new physically realistic scenes from object models downloaded from various online object repositories [29, 6] (see Table 1), using object cooccurrence statistics from SceneNet and optimising on the object positions within the scene with simulated annealing [31, 19].”
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation (2022, background): “Our object placement is most similar to [66, 20, 65, 62, 10], where we iteratively place objects on floors, walls, and surfaces and use semantic asset groups to sample objects that co-occur ( e.g. chairs next to tables).”
Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation (2020, background): “[74,64] propose learning hierarchical spatial priors between furniture, that is integrated into a hand-crafted cost used to generate optimized indoor scene layouts.”
SceneNet: An annotated model generator for indoor scene understanding (2016, methodology): “It is deﬁned as in [30], where bb on,m is the sum of the half diagonal of the bounding box of m and the diagonal of the bounding box surrounding both o and n , while d on,m is the Euclidean distance between the centroid of the object m and the centroid of this overall bounding box. w on,m max(0 ,…”
SceneNN: A Scene Meshes Dataset with aNNotations (2016, background): “For example, object occurrence and co-occurrence probabilities can be extracted, which are commonly used for indoor scene synthesis [10, 39, 40].”
Discovering objects and their relations from entangled scene representations (2017, methodology): “2012) modelled relations among objects in scenes using tree structured context models. 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”
Diffusion-based Generation, Optimization, and Planning in 3D Scenes (2023, background): “Various tasks have been devised to achieve these goals, fostering downstream applications in motion generation [32, 69, 73, 90], motion planning [42, 43, 60, 75], grasp generation [25, 31, 34], navigation [1, 95], scene synthesis [24, 47, 72, 82], embodied perception and manipulation [30, 39, 61], a”
PiGraphs (2016, methodology): “The domain of scenes has also seen its share of data-driven methods in the line of work addressing scene synthesis [Yu et al. 2011; Fisher et al. 2012; Xu et al. 2014].”
A Review on Virtual Reality Skill Training Applications (2021, background): “Procedural generation of 3D virtual content is a common approach for creating certain types of 3D content [e.g., terrains Smelik et al., 2009, cities Parish and Müller, 2001, and room layouts Yu et al., 2011].”
Example-based synthesis of 3D object arrangements (2012, methodology): “Previous work addressing furniture layout used predefined sets of basic functional categories, such as “chairs” [Merrell et al. 2011; Yu et al. 2011].”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, methodology): “3D layout synthesis algorithms (Yu et al. 2011; Handa et al. 2016b) have been developed to optimize furniture arrange-123 (Fisher et al. 2012; Yu et al. 2016), and optimizing the number of objects in scenes using LARJ-MCMC (Yeh et al. 2012).”
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding (2016, background): “erstanding, which is closely related to our work. Scene 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 usua”
IM2CAD (2016, unknown): “Researchers have explored a variety of techniques to automatically compute CAD scene models using non-photographic means, e.g., using example based approaches [11], utilizing text descriptions [7], and optimizing for furniture arrangements in a given space [47, 28].”
Semantically-enriched 3D models for common-sense knowledge (2015, unknown): “The object attributes that we collected are critical for enabling automatic scene layout and scene synthesis applications explored by much prior work [18, 26, 7].”