Slashdot Mirror
Disney Research Creates Megastereo - Panoramas With Depth
mikejuk writes "Disney Research has made a breakthrough in implementing the technique of acquiring depth information from a simple camera scan of a scene. For a perfect panorama you need to rotate the camera around its optical center, i.e. just rotate the camera. However, if you just rotate the camera about itself you don't get any parallax effects — which is why it makes the stitching together easier. If you want to get 3D information from the sequence of shots you need parallax. This means rotating the camera mounted on an offset arm or just moving the camera along an arc in your outstretched hand. The big problem with this method is that the parallax makes it more difficult to fit the mosaic together, and this is the problem that the research team has been working on. Using a range of different scanning methods the results can be converted into high resolution panoramas automatically complete with 3D information."
Nice. Given Disney's interest in converting 2D movies to fake 3D movies, it's not surprising that they're investing in this. It looks like they're able to do this without having to create imagery to fill in occluded areas, which is a problem with some of the other approaches.
Next, Google StreetView needs to be redone with this level of quality.
When I was a kid my dad had a big console stereo in the living room. I believe it's brand was Columbia. It was huge and long, about the size of a sofa.
Back then, Walt Disney had a television show on Sunday nights that everybody watched. He'd personally introduce an interesting short film that we'd all watch.
It's a shame what corporate interests have done to his name.
Are there any algorithms out there that can take a movie, and produce a sharp photo (or a series of sharp photos)?
By "sharp", I mean much sharper than each of the individual frames of the movie.
I.e., the algorithm should use information between subsequent frames to sharpen the image.
If Pandora's box is destined to be opened, *I* want to be the one to open it.
They are largely responsible for never-ending copyrights which are really really bad. So screw them and everything they do.
The author has a weak grasp on how stitching software is affected by parallax. Also, it would still be technically easier to to with two cameras or a stereo camera.
I've been a long-time panoramic and 3D photography enthusiast, and have gigabytes of data that could be fed straight into this software.
Shooting a 3D photograph is easy (just take two frames, correct issues in software later); shooting panoramas is easy (let the stitchers do their job); shooting a 3D panorama has always been too much work for me.
It's a pity I can't get my hands on any working code yet, and any commercial product is probably way off in the future.
Also, here's a link to their paper[PDF] for those interested. It's quite readable.
It's based on this invention: http://www.vision.huji.ac.il/stereo/
Yael Pritch (who was involved in this project in Disney) was also involved in this research in the Hebrew University.
So it's a breakthrough, but a very old one and, more importantly, somebody else's
Isn't this similar to the 3D Sweep Panorama feature that has been available in some Sony cameras and smartphones since 2010?
http://www.sony.co.uk/hub/cyber-shot-digital-cameras/technology/article/3d-sweep-panorama
Anytime someone reads Disney creates they should substitute the word "copies" until proven otherwise. Disney has a long and storied history of intellectual property theft when it was in their best interest. They are arguably the greatest hypocrites in the world about IP, even more so than Hollywood themselves. They are always the ones that hold the most radical of views in the MPAA and are very quick to hold condemn anyone else and take away their rights. They have also been stealing from the public domain and other individuals for ideas for decades. A quick Google search can find example upon example of their bad behavior.
You can take a look yourself and listen to the difference.
http://saveie6.com/
I repeat: cross-eye is the only stereogram that does not require additional equipment AND allows normal 2D view if you do not feel like crossing your eye.
Why protein structure journals got it for at least 20 years now and general purpose 3D photography cannot get it?
I do not believe in karma. "Funny"=-6. Do good and forbid evil. Yours, Oft-Offtopic Flamebaiting Troll.
I wonder if it may by applied to old panoramic paintings:
http://en.wikipedia.org/wiki/Panoramic_painting
http://en.wikipedia.org/wiki/File:Panorama_of_London_Barker.jpg
I suppose it depends of how they were made.
You sure don't speak for as many people as you think you do. Otherwise there would be no market for it.
Many CGI effects simply 'redress' a real environment with 'digital makeup', say adding 'damage' to buildings. The algorithms that allow this are part of proprietary programs used by many special effect houses across the planet. Essentially, you shoot video footage, and the program calculates depth geometry to aid in extracting non-changing textures from the scene. The texture data is presented to artists as 2D 'photographs' that the artist can re-touch (adding the afore-mentioned building damage, for instance). The program can now apply this 'new' texture data to the original video, placing the artists work in the context of moving video shots.
In other words, imaging photo-shopping a SINGLE photograph of the front of a building. Now imagine shooting video including that building. Now imaging that your single photo-shopped image of the building appears throughout the video in the correct place.
This cheap-n-cheerful approach to CGI doesn't stand up to close scrutiny, so it tends to be used for background shots that won't challenge the lack of true in-scene 3D re-modelling.
And, of course, modern computer algorithms allow us to grab 3D scene data from almost any video, allowing the insertion of synthetic 3D CGI elements that track the camera movements perfectly.
Disney researchers in Guangdong Ni Hao Liaoning Guangxi Zhuang performed the research.
It's logo is Mickey Ni Hao Mouse
Center channel is L + R and WOW !! You are there !! Blow them Nikkos up real good !!
Check this out, an entire film made from SFM. Took me 3 years, did a lot of this *kinda* in the process of making my world, I just dropped photos all together and went for Point Clouds instead.
http://youtu.be/TSOJl8SNZLM
Sales figures (where it is possible to differentiate) suggest that 3D isn't really much of a selling point.