On being the right scale: sizing large collections of 3D models

22 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

ShapeNet: An Information-Rich 3D Model Repository (2015, methodology): “We estimate the absolute dimensions of models us-ing prior work in size estimation [25], followed by manual veriﬁcation.”
Semantically-enriched 3D models for common-sense knowledge (2015, methodology): “We use a 3D model size estimation method designed to propagate physical size priors between models in 3D scenes [20] to obtain physical sizes for our corpus.”
InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset (2018, background): “Although an excellent resource, the quality of the models and textures from these repositories can be quite variable and missing ground truth metric scales requires automated prediction [26, 27].”
Semantic Parsing for Text to 3D Scene Generation (2014, methodology): “In addition, we assume the models have been scaled to physically plausible sizes and oriented with consistent up and front direction (Savva et al., 2014).”
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth (2016, background): “Tackling this is a significant problem and some work has been done which could be useful in future iterations [21].”
SceneNet: An annotated model generator for indoor scene understanding (2016, methodology): “We use the results from [31] to scale our models appropriately.”