Monocular Surface Reconstruction Using 3D Deformable Part Models
| Autor: | Iasonas Kokkinos, Stefan Kinauer, Maxim Berman |
|---|---|
| Přispěvatelé: | Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec, Organ Modeling through Extraction, Representation and Understanding of Medical Image Content (GALEN), Ecole Centrale Paris-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Paris-Saclay, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Ecole Centrale Paris |
| Rok vydání: | 2016 |
| Předmět: |
Ground truth
Structured support vector machine Unary operation business.industry [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Inference 02 engineering and technology 010501 environmental sciences Object (computer science) 01 natural sciences Convolutional neural network [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Pairwise comparison Graphical model Artificial intelligence business 0105 earth and related environmental sciences Mathematics |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783319494081 ECCV Workshops (3) Geometry Meets Deep Learning Workshop in association with ECCV 2016 Geometry Meets Deep Learning Workshop in association with ECCV 2016, Oct 2016, Amsterdam, Netherlands. pp.296-308, ⟨10.1007/978-3-319-49409-8_24⟩ |
| DOI: | 10.1007/978-3-319-49409-8_24 |
| Popis: | International audience; Our goal in this work is to recover an estimate of an object's surface from a single image. We address this severely ill-posed problem by employing a discriminatively-trained graphical model: we incorporate prior information about the 3D shape of an object category in terms of pairwise terms among parts, while using powerful CNN features to construct unary terms that dictate the part placement in the image. Our contributions are threefold: firstly, we extend the Deformable Part Model (DPM) paradigm to operate in a three-dimensional pose space that encodes the putative real-world coordinates of object parts. Secondly, we use branch-and-bound to perform efficient inference with DPMs, resulting in accelerations by two orders of magnitude over linear-time algorithms. Thirdly, we use Structured SVM training to properly penalize deviations between the model predictions and the 3D ground truth information during learning. Our inference requires a fraction of a second at test time and our results outperform those published recently in [17] on the PASCAL 3D+ dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|