VizWorld.com

At SIGGRAPH Asia, researchers from Carnegie Mellon’s CS department are demonstrating an interesting new algorithm capable of matching not only similar images, but matching paintings and sketches against databases of images looking for matches.

The goal of this work is to find visually similar images even if they appear quite different at the raw pixel level. This task is particularly important for matching images across visual domains, such as photos taken over different seasons or lighting conditions, paintings, hand-drawn sketches, etc. We propose a surprisingly simple method that estimates the relative importance of different features in a query image based on the notion of “data-driven uniqueness”. We employ standard tools from discriminative object detection in a novel way, yielding a generic approach that does not depend on a particular image representation or a specific visual domain.

Impressive stuff, check out their demo video below.

via Data-driven Visual Similarity for Cross-domain Image Matching.

Science algorithm, siggraph

An amazing paper at SIGGRAPH2011 Asia from Kevin Karsch, Varsha Hedau, David Forsyth, Derek Hoiem shows some amazing algorithms they’ve developed for inserted rendered & artificial objects into photographs of real-scenes, all with a minimum of user input.

With a single image and a small amount of annotation, our method creates a physical model of the scene that is suitable for realistically rendering synthetic objects with diffuse, specular, and even glowing materials while accounting for lighting interactions between the objects and the scene. We demonstrate in a user study that synthetic images produced by our method are confusable with real scenes, even for people who believe they are good at telling the difference. Further, our study shows that our method is competitive with other insertion methods while requiring less scene information. We also collected new illumination and reflectance datasets; renderings produced by our system compare well to ground truth. Our system has applications in the movie and gaming industry, as well as home decorating and user content creation, among others.

There are some amazing applications of this technology, only the first of which is detailed in their abstract.  A little more automation and a nice simple web-driven/cloud-backed system and this could be the cornerstone of many technologies, not the least of which would be interior decorating.

Be sure to watch the video below.

Rendering Synthetic Objects into Legacy Photographs from Kevin Karsch on Vimeo.

via KevinKarsch.com

Science algorithm, siggraph

RealFlow has a great SIGGRAPH Demo Reel up on YouTube, showing some of the great work they’ve done for TV, Movies, and commercials over the last year or so.  You’ll recognize lots of soft drink commercials, body wash commercials, and a few big movie and video game scenes.  Check it out above.

Update 9/2: Seems RealFlow pulled the original video, I replaced it with the new version. Only different I see right away is new music.
via Siggraph 2011 Showreel – YouTube.

Graphics demo, realflow, reel, siggraph

FXGuide talks to two of the guys behind some of this year’s SIGGRAPH Computer Animation Festival entries, including some great details with Damian Nenow on his impressive geometric clouds in 3dsMax.

Most people would do clouds now as volumetric renders, but I didn’t want to use a volumetric solution because it’s hard to control them and know the final shape. So I created them first as low-poly geometry based clouds. Then, using the Vertex Color Tool in Max, which is an almost forgotten tool, I could use the vertex color data to illuminate the clouds in the way I wanted.

The way it worked was I created these low poly elements, then covered them with thousands of sprites. They had alpha channel textures on them. You can then add photorealistic textures, like photographs of fragments of actual clouds, or you can add hand-drawn ones, which is what I did. So that’s why they look pictorial. I was able to get very fast render times – between 10 to 30 seconds just using a simple scanline renderer.

The Vertex Color tool is far from forgotten in Scientific visualization arenas, we use it regularly here.  I can easily see how it’s not particularly useful amongst “normal” animation people tho.

via Behind the scenes with the Siggraph CAF winners | fxguide.

Graphics 3dsmax, animation, interview, short, siggraph

Anandtech has some great writeups on two new NVidia technologies that I’ve frankly been a bit surprised I haven’t seen press releases on.  The new NVidia Maximus and Quadro Virtual Graphics ideas both sound like big deals, but information has been scarce outside of a special demonstration event at SIGGRAPH.

First off is a new technology called “NVidia Maximus”, that voids the typical SLI-requirements of matching cards and lets you put a Quadro and a Tesla card in your computer at the same time, letting each of the two cards do what they’re best at.

So where does Maximus fit into this? By making the setup more economical. The obvious implementation of a multi-GPU workstation is to double up on Quadro cards. High-end Quadro cards are just as compute capable as Tesla cards – the Tesla C2070 is clocked exactly the same as a Quadro 6000 – but a Quadro 6000 is over $1000 more expensive than a Tesla C2070 on the open market. Since the ray-tracing task is entirely a compute task there’s no need for the second card to be a more expensive Quadro card when it could be a cheaper Tesla card, and that’s Maximus in a nutshell: using a Tesla card as a dedicated compute GPU to assist a Quadro card. It’s not necessarily groundbreaking, but for NVIDIA’s customers it would be a cheaper way to do real-time modeling and ray-tracing together.

The other technology, which I find vastly more interesting, is the NVidia Quadro Virtual Graphics Technology codenamed Monterey.  This technology is a driver modification allowing you to access remote graphics resources, Quadros of course, for remote rendering.    Added at the driver level like this, modifications of individual applications should be minimal, and it allows multiple users to take advantage of “cloud” like resources for visualization and rendering.  Think of it as your own private OnLive cloud, running your own applications.  Think of getting multi-Quadro performance on your little Laptop.

NVIDIA’s aspirations with the technology are fairly lofty as it’s an ecosystem product that ties together multiple products. Quadros would be server-side, while clients can be lower-powered Quadros (e.g. laptops) or even mobile Tegra-based products – both of which provide for the decoding of the H.264. The ultimate result would be that users could access the rendering power of Quadro cards remotely, from computers and mobile devices alike (ed: it’s the mainframe era all over again). Presumably NVIDIA has a use case in mind on the mobile side, as we’ve yet to see workstation-type software on a tablet or phone. The more immediate benefit would be the centralization of Quadro cards, allowing businesses to operate power-hungry Quadro cards in the controlled environment of a server room instead of menacing desktop users, and to establish a common pool of Quadro cards for a group of users rather than buying a Quadro card for each individual user.

This is also an important step forward for Nvidia’s growing ARM/Tegra business.  Allowing mobile Tegra devices, like the newer Tablets and Mobile Phones already using Tegra, to access remote Quadro resources for heavy graphics would be a huge step forward if the bandwidth was available.

via AnandTech – SIGGRAPH 2011: NVIDIA’s Upcoming Workstation Technologies – Project Maximus & Monterey Technology.

Hardware nvidia, siggraph

If you couldn’t make it to SIGGRAPH in Vancouver (like me), then you can enjoy at least the NVidia presentations via livestream on their Facebook page.

The theater will include demonstrations and real-life case studies that cover the latest in workstation professional graphics technologies. Open to all attendees, the theater is located in the NVIDIA booth and will feature both NVIDIA experts and industry luminaries. See below for the schedule of talks and speakers.

Today (Wednesday), they’ve got talks on CATIA V6, Maya, Enlighten, the new “Quadro Virtual Graphics Platform”, and lots of VFX talks.

NVIDIA Technology Theater on Facebook.

Graphics nvidia, siggraph

Adobe is demonstrating a new research project in the NVidia booth at SIGGRAPH, showing off some realtime raytracing effects for Adobe AfterEffects.  Using the power of Fermi GPU’s, they’re able to add effects like reflections and lighting into motion graphics all in real-time.  The Fermi GPU is so fast and their algorithm so optimized that they can actually scrub through the timeline in realtime.

What made it practical for Adobe to build this, and reach such high performance levels, was the NVIDIA OptiX ray tracing engine. Adobe worked with NVIDIA to leverage OptiX to build their new renderer in just a few months. The job of OptiX is to let the developer concentrate on rendering while it handles all the intricacies of making it go fast on the GPU – and Adobe’s results are proving it’s good at its job.

Check out the live demo below.

via Adobe & NVIDIA Team Up for Ray Traced Compositing.

Graphics adobe, nvidia, siggraph

Unfortunately, with SIGGRAPH2011 being held outside the Continential US, I wasn’t able to make it this year.  But my loss is your gain!

If you have any photos or video of amazing stuff at the show, send it in!  Shoot an email to [email protected] with anything you’ve got, and maybe we’ll feature it on the Website or in an upcoming VizWorld Podcast (with full attribution & links if requested).

So fire up those iPhones and start shooting!

Graphics, Hardware, Science feature, siggraph

If you swing by the NVidia booth at SIGGRAPH you’ll see one major eye catching feat:  A single workstation driving 12 full HD displays with uncompressed 1080P video simultaneously, thanks to the NVidia QuadroPlex 7000 and FusionIO.

“Working with Fusion-io, we’ve created an impressive, large-scale visualization technology demonstration at SIGGRAPH for show attendees,” said Jeff Brown, general manager, Professional Solutions Group, NVIDIA. “By combining Fusion’s ioMemory technology with our powerful QuadroPlex 7000, we’re demonstrating how to enable real-time color correction and processing of a dozen simultaneous uncompressed HD video streams – without being bottlenecked by disk speeds.”

In addition, you can head over to the Autodesk, Thinkbox, and Tweak booths to see similar demonstrations: Massive datasets being processed real-time thanks to the mind-blowing bandwidth available in the FusionIO SSD system.

All the details after the break.

Read more…

Graphics, Hardware autodesk, fusionio, nvidia, siggraph, thinkbox, tweak

Pixar’s got some nice news this week for SIGGRAPH, the release of RenderMan for Maya 5.0 coming up this fall.  It’s got lots of the new features from RenderMan Pro Server 16 and a few new ones as well.

RenderMan for Maya 5.0 showcases fundamental advancements in RenderMan’s ray tracing technology, including a new ray tracing hider, a radiosity cache, and physically plausible shading. In combination these new features allow artists to take full advantage of today’s high performance multi-core architectures and create photorealistic images with minimal setup, all within the artist-friendly user interface of RenderMan for Maya. Additionally, the process of shading and lighting has been dramatically accelerated with new lighting tools, including the robust re-rendering technology used in Toy Story 3 and Cars 2, as well as progressive ray-traced re-rendering for real time look development.

RenderMan for Maya 5.0 will be available for only $995, but a new student package will be available for $199/year along with some nice free Courseware educational material.

Full release after the break.

Read more…

Graphics maya, pixar, renderman, siggraph