ACM SIGGRAPH presented its 2011 awards during the annual conference keynote session on Monday, August 8 in Vancouver. Technical awardees are: Jim Kajiya, Steven Anson Coons Award; Rick Szeliski, Computer Graphics Achievement Award and Olga Sorkine, Significant New Researcher. The technical awardees, along with Charles Csuri, recipient of the Award for Lifetime Achievement in Digital Art also gave talks on August 8.
Steven Anson Coons Award
Jim Kajiya received the Steven Anson Coons Award for his numerous pioneering technical contributions to rendering and computer graphics hardware design.
Kajiya started his professional graphics career in 1973 at Evans and Sutherland Computer Corporation. Jim received a doctorate in computer science from the University of Utah in 1979. For the next 15 years he was on the faculty of the California Institute of Technology where he founded the graphics research group with Al Barr. He then joined Microsoft Research (MSR) in 1994 where he built and led the graphics group and eventually went on to become a director in the MSR lab in Redmond. He now contributes at MSR in his role as a Distinguished Engineer.
In 1991 Kajiya was honored with the SIGGRAPH Technical Achievement Award. In 1997, he, along with Timothy Kay, received a technical Academy Award for work on rendering hair and fur.
In 1993 he served as the technical program chair for SIGGRAPH 1993. In this role he transformed the paper review process into one that has been widely emulated. He has also served on the SIGGRAPH executive committee.
Kajiya is perhaps best known as the sole author of the seminal paper “The Rendering Equation” published in ACM SIGGRAPH 1986. Building on ideas published in SIGGRAPH such as the radiosity algorithm and Pixar’s Distributed Ray Tracing technique, he advanced the application of radiative transfer to the problem of rendering. He recognized that various approximations to the series solution to the resulting integral equation encompassed virtually all known rendering algorithms. He showed how to use Monte-Carlo Markov Chain approximations to the solution to generate pictures with a better visual fidelity than any previously produced. His path tracing algorithm remains the gold standard. In succinct paragraphs, he also describes importance sampling and several approaches to hierarchical subdivision of the image plane for variance-reduction.
In addition to developing foundational mathematics and associated algorithms for computer graphics, Kajiya has also been instrumental in hardware for graphics. He designed the Evans & Sutherland frame buffer, a device of significance for early raster graphics work at the University of Utah, New York Institute of Technology, JPL, and Cornell. Frame buffers are found inside every PC, tablet, and smartphone today. At Microsoft, he was also the principal architect on Talisman, advancing ideas such as texture compression and anisotropic filtering that are found in most current low-level 3D graphics standards.
Computer Graphics Achievement Award
The recipient of the 2011 Computer Graphics Achievement Award, Richard Szeliski is recognized for his pioneering contributions at the intersection of computer graphics and computer vision, particularly his work in image-based modeling and rendering. His work has significantly advanced the ability to capture the world in photographs and video and has shown how these advances enable a wide variety of new applications.
Szeliski has spent decades pursuing image-based rendering, computational photography, video scene analysis, and the use of computer vision to build 3D models from images. He has published two books and well over 100 research papers in computer vision, computer graphics, and medical imaging. He currently leads the Interactive Visual Media Group at Microsoft Research, where he has worked since 1995. He also holds an Affiliate Professor appointment at the University of Washington. Prior to Microsoft, he worked at Bell-Northern Research, Schlumberger, SRI International, and Digital’s Cambridge Research Laboratory.
A hallmark of Szeliski’s work is the insight that it is often not necessary to solve the entire computer vision problem of reconstructing a full 3D model from imagery; for many applications it is sufficient to re-render the input imagery using a simpler proxy model. In a world where image (and video) capture and distribution has become increasingly easy, this insight means that high-quality computer graphics experiences can be delivered without high-fidelity 3D models. Szeliski and his collaborators have developed several new representations that leverage this insight and consequently changed the way computer graphics researchers think about capturing the world. Layered depth images showed that incorporating just one extra channel per pixel (depth) leads to efficient re-rendering of imagery from nearby camera views. His work on the Lumigraph went towards the other extreme and showed that it is enough to sample the light emanating in all directions from an object in order to synthesize new views of the object.
Szeliski has also worked to develop practical new applications supported by cutting edge research. Algorithms for image stitching now allow people to capture hundreds of overlapping images of a scene, and then fully-automatically create a seamless panorama over which a viewer can pan and zoom interactively. Here, the challenges are to perform feature matching for image alignment and seamless blending of a large, unorganized set of photographs. He has also done pioneering work in other areas of computational photography, including merging images with different exposures and flash and non-flash images, as well as extending these approaches to the temporal domain by aligning, blending, and looping video clips and sequences.
In the Photo Tourism work, collections of photos taken of a scene by different photographers at different times can be combined to allow people to virtually tour the location by flying from one photograph to another. Again, the challenge is to find common feature points in a large, unorganized set of photographs, but in this case, where the camera parameters are very different in each photo. Surprisingly, this kind of input data can lead to an accurate cloud of points in 3D, which serves as a proxy model for locating and transitioning between photos.
Throughout his research career, Szeliski has combined a deep understanding of the mathematical underpinnings of image capture and rendering with an encyclopedic knowledge of available methods and brought these to bear in new and creative applications at the intersection of computer graphics and computer vision.
Significant New Researcher Award
SIGGRAPH is proud to recognize Olga Sorkine as the 2011 recipient of the Significant New Researcher Award. Her outstanding early contributions to the field of geometry processing, particularly her highly influential graduate research on differential coordinates, and her subsequent work on interactive mesh editing have already had a huge impact; her recent entry into new areas like color harmonization, video retargeting, and visualization demonstrate her breadth.
Sorkine grew up in Tel Aviv, and got her B.Sc. (2000) and Ph.D. (2006) from Tel Aviv University, after which she spent two years in a postdoctoral appointment at the Technical University of Berlin. She then took an Assistant Professor position at New York University, and as of 2011 has joined the faculty at ETH Zurich. She received an Alexander von Humbolt Fellowship in 2006, and the Eurographics Young Researcher award in 2008.
The idea behind differential coordinates is to represent the geometry of meshes by encoding locally-defined details rather than absolute positions of mesh vertices. This approach can be viewed as generalizing gradient domain representations for images to meshes in three-space, and leads to versatile geometric modeling and processing techniques. This generalization presents significant challenges, many of which were addressed in a series of papers that Sorkine co-authored in 2004-2007, such as “Laplacian surface editing” (SGP 2004), “Linear rotation-invariant coordinates for meshes” (SIGGRAPH 2005), and “As-rigid-as-possible surface modeling” (SGP 2007). In work on detail preserving deformation, she and her coauthors showed that the optimization problems that arise can be solved at interactive rates, and applied the technique to such problems as character animation, sketch-based shape editing, and image manipulation.
The theme of interactivity in mesh processing has continued with her more recent work on FiberMesh (SIGGRAPH 2007) and iWires (SIGGRAPH 2009). Fibermesh is an artist-friendly system that allows users to create and edit 3D models using an arbitrary collection of sketched curves, and iWires makes manipulation of man-made objects far easier by discovering and preserving important design features such as symmetries.
Sorkine has also demonstrated enormous breadth of interests; in just the last two years she’s produced papers on image and video retargeting, reverse tone mapping, volumetric modeling, and visualization.