{"type":"ScholarlyArticle","title":"A Stochastic Image Grammar for Fine-Grained 3D Scene Reconstruction","authors":[{"name":"Xiaobai Liu","slug":"xiaobai-liu","given":"Xiaobai","family":"Liu","affiliation":""},{"name":"Yadong Mu","slug":"yadong-mu","given":"Yadong","family":"Mu","affiliation":""},{"name":"Liang Lin","slug":"liang-lin","given":"Liang","family":"Lin","affiliation":""}],"abstract":"This paper presents a stochastic grammar for fine-grained 3D scene reconstruction from a single image. At the heart of our approach is a small number of grammar rules that can describe the most common geometric structures, e.g., two straights lines being co-linear or orthogonal, or that a line lying on a planar region etc. With these grammar rules, we re-frame single-view 3D reconstruction problem as jointly solving two coupled sub-tasks: i) segmenting of image entities, e.g. planar regions, straight edge segments, and ii) optimizing pixel-wise 3D scene model through the application of grammar rules over image entities. To reconstruct a new image, we design an efficient hybrid Monte Carlo (HMC) algorithm to simulate Markov Chain walking towards a posterior distribution. Our algorithm utilizes two iterative dynamics: i) Hamiltonian Dynamics that makes proposals along the gradient direction to search the continuous pixel-wise 3D scene model; and ii) Cluster Dynamics, that flip the colors of clusters of pixels to form planar region partition. Following the Metropolis-hasting principle, these dynamics not only make distant proposals but also guarantee detail-balance and fast convergence. Results with comparisons on public image dataset show that our method clearly outperforms the alternate state-of-the-art single-view reconstruction methods.","doi":null,"url":"https://ijcai.org/proceedings/2016/484","pdf":"https://ijcai.org/proceedings/2016/0484.pdf","markdown":"https://ijcai.org/proceedings/2016/484.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/484","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":484,"pages":{"first":3425,"last":3430},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}