Download presentation
Presentation is loading. Please wait.
Published byKatrina Hunter Modified over 9 years ago
1
Creating and Exploring a Large Photorealistic Virtual Space INRIA / CSAIL / Adobe First IEEE Workshop on Internet Vision, associated with CVPR 2008.
2
Outline Introduction Constructing the image space Navigating the virtual 3D space Limitations and Conclusion
3
Introduction We present a system for exploring large collections of photos in a virtual 3D space. Let users navigate within each theme using intuitive 3D controls that include move left/right, zoom and rotate.
4
In a similar fashion we can create infinite zoom effects that resemble the ”Droste effect”.
5
Constructing the image space The image database – We have collected ~6 million images from Flickr based on keyword and group searches typical image size is 500x375 pixels 720GB of disk space (jpeg compressed)
6
Image representation Color layout GIST [Oliva and Torralba’01] Original image
7
Obtaining semantically coherent themes We further break-up the collection into themes of semantically coherent scenes: Train SVM-based classifiers from 1-2k training images [Oliva and Torralba, 2001]
8
Basic camera motions Forward motionCamera rotation Camera pan Starting from a single image, find a sequence of images to simulate a camera motion:
9
3. Find a match to fill the missing pixels Scene matching with camera view transformations: Translation 1. Move camera 2. View from the virtual camera 4. Locally align images 5. Find a seam 6. Blend in the gradient domain
10
4. Stitched rotation Scene matching with camera view transformations: Camera rotation 1. Rotate camera 2. View from the virtual camera 3. Find a match to fill-in the missing pixels 5. Display on a cylinder
11
Steps Collect images Classify images into topic themes Calculate the descriptors: – GIST – RGB Build the graph Find the path for given query image(s) – Dijkstra algorithm Alignment – Gradient decent alignment Composition – Poisson blending
12
More “infinite” images – camera translation
13
Forward Rotate (left/right) Pan (left/right) Nodes represent Images Edges represent particular motions: Edge cost is given by the cost of the image match under the particular transformation Image graph Navigating the virtual 3D space Virtual space as an image graph
14
Virtual image space laid out in 3D
15
Limitations and Conclusion The larger the database, the better the results. Compositing two distinct images is always a challenge and at times, the seam is quite visible. This system can be used to create photorealistic visual content for large online virtual 3D worlds like Second Life. Create infinite panoramas or use the image taxi to generate tailor-made tours in the virtual 3D space. These applications can find use in games, movies and other media creation processes.
17
Thank you !
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.