Abstract
We propose a new approach to perform object shape retrieval from images, it can handle the shape of the part of the object and combine parts from different sources to find a different 3D shape. Our method creates a common representation for images and 3D models that enables mixing elements from both kinds of inputs. Our approach automatically extracts the desired part and its 3D shape from each source without the need of annotations. There are many applications to combining parts from images and 3D models, for example, performing smart online catalogue searches by selecting the parts that we are looking for from images or 3D models and retrieve a 3D shape that has the desired arrangement of parts. Our approach is capable of obtaining the shape of the parts of an object from an image in the wild, independently of the pose of the object and without the need of annotations of any kind.
Highlights
The widespread availability of low cost high quality cameras and 3D sensing devices has recently enabled the computer vision and graphics communities to collect and curate vast Internet collections of images and 3D shapes of everyday objects such as ImageNet or ShapeNet
While most tools developed so far have dealt with shape and appearance modalities separately, some recent methods [2], [3] have begun to exploit the complementary nature of these two sources of information and to reap the benefits of creating a common representation for images and 3D models
LEARNING SHAPE EMBEDDINGS FOR OBJECT PARTS While the overall goal of our approach is to obtain a joint representation for images and 3D models, following recent work [2], we choose to create an embedding space that captures the similarity between the shape of object parts based exclusively on the 3D shapes
Summary
The widespread availability of low cost high quality cameras and 3D sensing devices has recently enabled the computer vision and graphics communities to collect and curate vast Internet collections of images and 3D shapes of everyday objects such as ImageNet or ShapeNet. The widespread availability of low cost high quality cameras and 3D sensing devices has recently enabled the computer vision and graphics communities to collect and curate vast Internet collections of images and 3D shapes of everyday objects such as ImageNet or ShapeNet These datasets have quickly become the cornerstone of tasks such as visual recognition and 3D scene understanding and have led to huge progress since they represent the labelled examples from which machines can reason about shape and appearance. As these databases of images and 3D shapes keep growing in size and number, organizing and exploring them has become increasingly complex. Creating a joint embedding for images and 3D models allows to retrieve 3D
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
