Novel Views of Objects from a Single Image

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 v...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on pattern analysis and machine intelligence Ročník 39; číslo 8; s. 1576 - 1590
Hlavní autoři: Rematas, Konstantinos, Nguyen, Chuong H., Ritschel, Tobias, Fritz, Mario, Tuytelaars, Tinne
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.08.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
2D to 3D alignment
Automobiles
Computer simulation
Core loss
Geometry
image based rendering
Microprocessors
Novel view synthesis
Performance enhancement
Rendering (computer graphics)
Shape
Solid modeling
Synthesis
Three dimensional models
Three-dimensional displays
Two dimensional displays
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2016.2601093