Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Reasoning from Blocks to Stability

By Zhaoyin Jia, Andrew C. Gallagher, Ashutosh Saxena, Tsuhan Chen

How researchers see this paper

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

Citations in the corpus

Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow (2018, background): “While physical properties and interactions of objects have long been of interest for computer vision problems [24, 34, 13], addressing physics problems with deep learning algorithms is an area of particular interest in recent years.”
Learning Physical Intuition of Block Towers by Example (2016, background): “For example, (Jia et al., 2015) ﬁt cuboids to RGBD data and use their centroids to search for scene interpretations that are statically stable.”
Physics 101: Learning Physical Object Properties from Unlabeled Videos (2016, methodology): “Our incorporation of physical laws into our model distinguish our framework from previous methods introduced in the computer vision and robotics community for predicting physical interactions or properties of objects for various purposes [4, 5, 9, 12, 16, 21, 22, 26].”
ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking (2018, background): “Examples include reasoning about support relations [15,16] and their geometric affordances and inferring forces in Newtonian image understanding [17].”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, background): “Recent work has successfully incorporated high-level information such as gravity, intersection, and stability [46, 30, 29].”
Scene Understanding by Reasoning Stability and Safety (2015, background): “Jiang et al (2013) and Jiang and Saxena (2013) proposed scene labeling algorithms by considering humans as the hidden context.”