Rematas, K;
Nguyen, CH;
Ritschel, T;
Fritz, M;
Tuytelaars, T;
(2016)
Novel Views of Objects from a Single Image.
IEEE Transactions on Pattern Analysis and Machine Intelligence
10.1109/TPAMI.2016.2601093.
(In press).
Preview |
Text
Rischel_1602.00328v2.pdf - Accepted Version Download (6MB) | Preview |
Abstract
Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not easily revertible. As a consequence, possibilities of changing viewpoint are limited. Given a single image depicting an object, novel-view synthesis is the task of generating new images that render the object from a different viewpoint than the one given. The main difficulty is to synthesize the parts that are disoccluded; disocclusion occurs when parts of an object are hidden by the object itself under a specific viewpoint. In this work, we show how to improve novel-view synthesis by making use of the correlations observed in 3D models and applying them to new image instances. We propose a technique to use the structural information extracted from a 3D model that matches the image object in terms of viewpoint and shape. For the latter part, we propose an efficient 2D-to-3D alignment method that associates precisely the image appearance with the 3D model geometry with minimal user interaction. Our technique is able to simulate plausible viewpoint changes for a variety of object classes within seconds. Additionally, we show that our synthesized images can be used as additional training data that improves the performance of standard object detectors.
| Type: | Article |
|---|---|
| Title: | Novel Views of Objects from a Single Image |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TPAMI.2016.2601093 |
| Publisher version: | http://dx.doi.org/10.1109/TPAMI.2016.2601093 |
| Language: | English |
| Additional information: | © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. |
| Keywords: | Three-dimensional displays, Solid modeling, Shape, Geometry, Two dimensional displays, Rendering (computer graphics), Automobiles, Image Based Rendering, Novel View Synthesis, 2D to 3D Alignment |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/1501229 |
Archive Staff Only
 |
View Item |
