News

The 23rd ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2024) Early Career Researcher Award is presented to Minchen in recognition of his contributions to enhancing the robustness, efficiency, and fidelity of physics-based animation techniques. His work on adaptive discretization and data-driven simulation has significantly advanced the field, with broad applications in computer animation, virtual reality, computational mechanics, and robotics.

Carnegie Mellon's research is well-represented at SIGGRAPH 2024, with Carnegie Mellon authors collaborating on 13 papers, including two best papers (🏆) and two honorable mentions (🏅) in the SIGGRAPH Technical Papers Awards .

• A Dynamic Duo of Finite Elements and Material Points
  Xuan Li, Minchen Li, Xuchen Han, Huamin Wang, Yin Yang, and Chenfanfu Jiang
• A Heat Method for Generalized Signed Distance
  Nicole Feng and Keenan Crane
• AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion
  Mohamad Qadri*, Kevin Zhang*, Akshay Hinduja, Michael Kaess, Adithya Pediredla, and Christopher Metzler
• Aperture-aware lens design
  Arjun Teh, Ioannis Gkioulekas, and Matthew O'Toole
• I♥Mesh: A DSL for Mesh Processing
  Yong Li, Shoaib Kamil, Keenan Crane, Alec Jacobson, and Yotam Gingold
• Minkowski Penalties: Robust Differentiable Constraint Enforcement for Vector Graphics
  Jiří Minarčík, Sam Estep, Wode Ni, and Keenan Crane
• Ray Tracing Harmonic Functions (honorable mention 🏅)
  Mark Gillespie, Denise Yang, Mario Botsch, and Keenan Crane
• Repulsive Shells (best paper 🏆)
  Josua Sassen, Henrik Schumacher, Martin Rumpf, and Keenan Crane
• Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models
  Zhipeng Bao, Yijun Li, Krishna Kumar Singh, Yu-Xiong Wang, and Martial Hebert
• Solid Knitting (honorable mention 🏅)
  Yuichi Hirose, Mark Gillespie, Angelica M. Bonilla Fominaya, and James McCann
• Strategy and Skill Learning for Physics-based Table Tennis Animation
  Jiashun Wang, Jessica Hodgins, and Jungdam Won
• VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
  Ying Jiang*, Chang Yu*, Tianyi Xie*, Xuan Li*, Yutao Feng, Huamin Wang, Minchen Li, Henry Lau, Feng Gao, Yin Yang, and Chenfanfu Jiang
• Walkin' Robin: Walk on Stars with Robin Boundary Conditions (best paper 🏆)
  Bailey Miller*, Rohan Sawhney*, Keenan Crane†, and Ioannis Gkioulekas†

In the author lists above, * and † indicate equal contribution.

Bailey Miller, Hanyu Chen, Alice Lai, and Ioannis Gkioulekas won the CVPR 2024 Best Student Paper Honorable Mention Award for their work "Objects as volumes: A stochastic geometry view of opaque solids." Check out the project website for details.

"CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting" by Peter Schaldenbrand, Gaurav Parmar, Jun-Yan Zhu, James McCann, and Jean Oh won the ICRA 2024 Best Paper award for Human-Robot Interaction and was the finalist for the Best Demonstration system and the ICRA Expo. Please check out the project website for details.

Jun-Yan was named a 2023 Packard Fellow for his work with Generative AI. Jun-Yan's work emphasizes new ways for creators to collaborate with generative models, while retaining control over the creative process and receiving proper compensation. His group has led several initiatives such as Concept Ablation, which can remove copyrighted materials and artworks of living artists from existing models, and Data Attribution, designed to facilitate compensation for creators whose work has been used in model training. The Packard Fellowship for Science and Engineering is the largest award given to young faculty in STEM fields, and is widely regarded as one of the most prestigious awards given to junior faculty members. An advisory panel of distinguished scientists and engineers carefully reviews the nominations and selects 20 fellows to receive an award of $875,000, distributed over five years, to allow the nation’s most promising early-career scientists and engineers flexible funding to take risks and explore new frontiers in their fields of study. Among the eight Packard Fellows currently at CMU, three are faculty members of the Graphics Lab, including previous awardees Jessica K. Hodgins (1994) and Keenan Crane (2018). Congratulations, Jun-Yan!

Yingsi Qin, Wei-Yu Chen, Matthew O'Toole, and Aswin C. Sankaranarayanan won the SIGGRAPH 2023 Best Paper Award for their work "Split-Lohmann Multifocal Displays." Check out the project website for details.

CMU Graphics members Mark Sheinin, Dorian Chan, Matthew O'Toole, and Srinivasa Narasimhan won CVPR 2022 Best Paper Honorable Mention for their work Dual-Shutter Optical Vibration Sensing. Check out the project webpage for details: https://imaging.cs.cmu.edu/vibration/

Yannis has received the National Science Foundation CAREER award. This is the NSF's most prestigious award which recognizes early-career faculty who lead advances in their fields and serve as positive role models in research and education. Yannis' CAREER award emphasizes computational interferometric imaging, which provides new imaging capabilities critical for applications in medical imaging, industrial fabrication, and material sciences.

CMU Graphics will be at SIGGRAPH Asia 2020!

• Path Tracing Estimators for Refractive Radiative Transfer
  Adithya Pediredla, Yasin Karimi Chalmiani, Matteo Giuseppe Scopelliti, Maysam Chamanzar, Srinivasa Narasimhan, and Ioannis Gkioulekas
• Rendering Near-Field Speckle Statistics in Scattering Media
  Chen Bar, Ioannis Gkioulekas, and Anat Levin
• Repulsive Curves
  Chris Yu, Henrick Schumacher, Keenan Crane
• You Can Find Geodesic Paths in Triangle Meshes by Just Flipping Edges
  Nicholas Sharp, Keenan Crane

Nick Sharp won the Best Student Paper Award at the 2020 Symposium on Geometry Processing for his work on a Laplace operator for point clouds and nonmanifold polygon meshes. The Laplacian is a basic building block for algorithms in digital geometry processing and simulation. Nick's work makes it possible to apply this tool reliably to any mesh or point cloud, even if it has bad connectivity or poor-quality triangles. Congrats, Nick!

Keep an eye out for these CMU Graphics papers at SIGGRAPH 2020!

• Interferometric Transmission Probing With Coded Mutual Intensity
  Alankar Kotwal, Anat Levin, Technion, Ioannis Gkioulekas
• KRISM – Krylov Subspace-Based Optical Computing of Hyperspectral Images
  Vishwanath Saragadam, Aswin Sankaranarayanan
• Langevin Monte Carlo Rendering With Gradient-Based Adaptation
  Fujun Luan, Shuang Zhao, Kavita Bala, Ioannis Gkioulekas
• Monte Carlo Geometry Processing: A Grid-Free Approach to PDE-Based Methods on Volumetric Domains
  Rohan Sawhney, Keenan Crane
• Path-Space Differentiable Rendering
  Cheng Zhang, Bailey Miller, Kai Yan, Ioannis Gkioulekas, Shuang Zhao
• Penrose: From Mathematical Notation to Beautiful Diagrams
  Katherine Ye, Wode Ni, Max Krieger, Dor Ma’ayan, Jenna Wise, Jonathan Aldrich, Joshua Sunshine, Keenan Crane
• Towards Occlusion-Aware Multifocal Displays
  Jen-Hao Rick Chang, Anat Levin, B. V. K. Vijaya, Kumar, Aswin C. Sankaranarayanan

Chao Liu, Srivnivasa Narasimhan, and collaborators at CMU and Rice University receive Best Paper Honorable Mention award at the 2020 IEEE International Conference on Computational Photography (ICCP) for their paper titled High Resolution Diffuse Optical Tomography using Short Range Indirect Subsurface Imaging.

Keenan has received the 2020 National Science Foundation CAREER award. This is the NSF's most prestigious award which recognizes early-career faculty who lead advances in their fields and serve as positive role models in research and education. Keenan's works is in Discrete Differential Geometry which builds fundamental representations and practical algorithms for processing and analyzing real-world geometric data by leveraging insights from differential geometry. Read more about it here.

The Sloan Foundation has named Ioannis Gkioulekas as a 2020 Sloan Research Fellow. The Sloan Research Fellowship highlights the contributions of early-career scientists and scholars who demonstrate outstanding promise in fundamental research. Gkioulekas' interests are in computational imaging, computer vision, and computer graphics. His work focuses on non-line-of-sight imaging which enables the imaging of objects obstructed by corners or scattering materials. Read more about it here.

CMU Graphics members Shumian Xin, Ioannis Gkioulekas, and Srinivasa Narasimhan, CMU ECE Professor Aswin Sankaranarayanan, and collaborators from U. Toronto won CVPR 2019 Best Paper Award forA theory of Fermat Paths for Non-Line-of-Sight Shape Reconstruction. Their paper was selected out of roughly 5000 submitted papers. The awards committee described the paper: “this paper makes significant advances in non-line-of-sight reconstruction — in essence the ability to see around corners. It is a beautiful paper theoretically, as well as inspiring. It continues to push the boundaries of what is possible in computer vision.”

Lots of amazing work from CMU Graphics to appear at SIGGRAPH 2019—check it out!

• Visual Knitting Machine Programming
  Vidya Narayanan*, Kui Wu*, Cem Yuksel, Jim McCann
• Navigating Intrinsic Triangulations
  Nicholas Sharp, Yousuf Soliman, Keenan Crane
• Symmetric Moving Frames
  Etienne Corman, Keenan Crane
• The Vector Heat Method
  Nicholas Sharp, Yousuf Soliman, Keenan Crane
• A Monte Carlo Framework for Rendering Speckle Statistics in Scattering Media
  Chen Bar, Marina Alterman, Ioannis Gkioulekas, Anat Levin
• Ellipsoidal Path Connections for Time-gated Rendering
  Adithya Pediredla, Ashok Veeraraghavan, and Ioannis Gkioulekas
• Wave-based Non-Line-of-Sight Imaging using Fast f-k Migration
  David B. Lindell, Gordon Wetzstein, Matthew O'Toole
• Non-Line-of-Sight Imaging with Partial Occluders and Surface Normals
  Felix Heide, Matthew O'Toole, Kai Zang, David B. Lindell, Steven Diamond, Gordon Wetzstein
• Neural Volumes: Learning Dynamic Renderable Volumes From Images
  Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, Yaser Sheikh
• VR Facial Animation via Multiview Image Translation
  Shih-En Wei, Jason Saragih, Tomas Simon, Adam W. Harley, Stephen Lombardi, Michal Perdoch, Alexander Hypes, Dawei Wang, Hernan Badino, Yaser Sheikh

Katherine Ye has been named a 2019 Microsoft Research PhD Fellow. She joins 10 students nationwide whose PhD research will be supported by MSR for the next two years. Katherine's work is making it possible to automatically turn plain-text mathematical equations into beautiful diagrams—find out more at http://penrose.ink. Congrats Katherine!

Our very own Jessica Hodgins has been named an ACM Fellow for her contributions to character animation, human simulation and humanoid robotics. The ACM Fellowship recognizes excellence, as evidenced by technical, professional and leadership contributions that advance computing, promote the free exchange of ideas, and advance the objectives of ACM. Read all about Jessica's award here. Congrats Jessica!

Keenan Crane has been named a 2018 Packard Fellow. The Packard Fellowships in Science and Engineering are among the nation’s largest nongovernmental fellowships, supporting blue-sky thinking of scientists and engineers in the hopes that their research will lead to new discoveries that improve people’s lives and enhance our understanding of the universe. Crane's work explores how the shapes and motions we observe in nature can be faithfully expressed in a language that is completely finite and discrete, and can hence be understood by computers. Read more about it here.

We'll be presenting a bunch of new work at SIGGRAPH 2018. Take a look!

• Variational Surface Cutting
  Nick Sharp, Keenan Crane (Carnegie Mellon University)
• Developability of Triangle Meshes
  Oded Stein, Eitan Grinspun (Columbia University), Keenan Crane (Carnegie Mellon University)
• Boundary First Flattening
  Rohan Sawhney Keenan Crane (Carnegie Mellon University)
• Optimal Cone Singularities for Conformal Flattening
  Yousuf Soliman, Dejan Slepcev, Keenan Crane (Carnegie Mellon University)
• Rapid Deployment of Curved Surfaces via Programmable Auxetics
  Mina Konakovic (EPFL), Julian Panetta (New York University), Keenan Crane (Carnegie Mellon University), Mark Pauly (EPFL)
• Learning Basketball Dribbling Skills Using Trajectory Optimization and Deep Reinforcement Learning
  Libin Liu (DeepMotion Inc.), Jessica Hodgins (Carnegie Mellon University)
• Skaterbots: Optimization-Based Design and Motion Synthesis for Robotic Creatures with Legs and Wheels
  Moritz Geilinger, Roi Poranne (ETH Zurich), Ruta Desai (Carnegie Mellon University), Bernhard Thomaszewski (Universite de Montreal), Stelian Coros (ETH Zurich)
• Automatic Machine Knitting of 3D Meshes
  Vidya Narayanan, Lea Albaugh, Jessica Hodgins, Stelian Coros, Jim McCann (Carnegie Mellon University)
• Scanner: Efficient Video Analysis at Scale
  Alex Poms (Carnegie Mellon University), William Crichton, Pat Hanrahan (Stanford University), Kayvon Fatahalian (Carnegie Mellon University)
• Slang: Language Mechanisms for Building Extensible Real-time Shading Systems
  Yong He, Kayvon Fatahalian (Carnegie Mellon University), Tim Foley (NVIDIA Research)
• Deep Appearance Models for Face Rendering
  Stephen Lombardi, Tomas Simon, Jason Saragih, Yaser Sheikh (Carnegie Mellon University)

We are very happy to welcome Matthew O'Toole to the CMU Graphics Group.  Matt will join us this fall as a faculty member with joint appointments in the Robotics Institute and Computer Science Department; he does fundamental work in computational imaging, a field that combines optics, electronics, and processing in new and interesting ways to capture and display visual information. In particular, he's interested in using programmable lights and cameras to analyze the world around us.  Matt received his PhD from the University of Toronto in 2016, and is currently a postdoc at Stanford. Welcome to CMU, Matt!

Jim McCann joins the CMU Graphics Group this fall, as a faculty member in the Robotics Institute. Jim is interested in systems and interfaces that operate in real-time and build user intuition; lately, he has been applying these ideas to textiles fabrication and machine knitting in the Carnegie Mellon Textiles Lab. He obtained his PhD in 2010 in the Graphics Lab, after which he worked at Adobe's Creative Technologies Lab and Disney Research. In his spare time, he makes video games as TCHOW llc. Welcome, Jim!

In election results announced August 19th, 2017, Jessica Hodgins was elected SIGGRAPH President. She will begin her three year term on September 1st. If you have ideas on how to improve either the organization or the conference, send them her way. And volunteer -- both the organization and the conference are in need of volunteers.

This year, nine papers that were authored or co-authored by graphics lab members will be presented at SIGGRAPH 2017:

• A Computational Design Tool for Compliant Mechanisms
  Vittorio Megaro, Jonas Zehnder, Moritz, Baecher, Stelian Coros, Markus Gross, Bernhard Thomaszewski
• Computational Design of Telescoping Structures
  Christopher Yu, Stelian Coros, Keenan Crane
• Epipolar Time of Flight Imaging
  Supreeth Achar, Joe Bartels, Red Whittaker, Kyros Kutulakos, Srinivasa G. Narasimhan
• Learning to Schedule Control Fragments for Physics-based Characters Using Deep Q-Learning
  Libin Liu, Jessica Hodgins
• Lightweight Structure Design Under Force Location Uncertainty
  Erva Ulu, Jim McCann, Levent Burak Kara
• Momentum-mapped Inverted Pendulum Models for Controlling Dynamic Human Motions
  Taesoo Kwon, Jessica K. Hodgins
• Shader Components: Modular and High Performance Shader Development
  Yong He, Tim Foley, Teguh Hofstee, Haomin Long, Kayvon Fatahalian
• Interactive Design of Animated Plushies
  James M. Bern, Kai-Hung Chang, Stelian Coros
• A Deep Learning Approach for Generalized Speech Animation
  Sarah Taylor, Taehwan Kim, Moshe Mahler, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, Yisong Yue, Iain Matthews

At SIGGRAPH this year, Jessica Hodgins will receive the Steven Anson Coons Award, which recognizes long-term creative impact on the field of computer graphics through a personal commitment over an extended period of time. She joins the ranks of other terrific members of our community including Ivan E. Sutherland, Pierre Bézier, Donald P. Greenberg, David C. Evans, Andries van Dam, Edwin Catmull, Jose Encarnação, James D. Foley, James F. Blinn, Lance Williams, Pat Hanrahan, Tomoyuki Nishita, Nelson Max, Rob Cook, Jim Kajiya, Turner Whitted, and Henry Fuchs. Congrats, Jessica!

Tonight, RI Faculty alum Iain Matthews (right) and his collaborators at Weta will be awarded a plaque for their facial capture system and RI PhD alum Kiran Bhat (left) and his ILM collaborators will get a certificate for their facial capture system.  

In a daring feat of housekeeping the brilliant students comprising the CMU Graphics Lab made the world a little cleaner place.

Two of our PhD students, Yong He (left) and Nick Sharp (right), were both recently awarded prestigious PhD fellowships. Yong, who is a fourth-year PhD student with Kayvon Fatahlian, will receive an NVIDIA fellowship, supporting his work on automated optimization of rendering systems. Nick, who is a first-year PhD student with Keenan Crane, is the recipient of an NSF Graduate Research Fellowship (GRFP), which will help jump start his work in 3D geometry processing. Congrats, guys!

A very warm welcome to our 2015 incoming graphics students, pictured here in Schenley Park, near the CMU campus.  Left to right: Ye Han, Alex Poms, James Bern, Chris Yu, Nick Sharp, Maria Khutoretsky, and Genesis Vasquez.  (Not pictured: Ravi Teja Mullapudi.)  Best of luck on the adventure!

Eight papers co-authored by graphics lab members will be presented at SIGGRAPH 2015 in Los Angeles, CA:

• Homogeneous Codes for Energy Efficient Illumination and Imaging
  Matthew O'Toole, Supreeth Achar, Srinivasa Narasimhan, Kiriakos Kutulakos
• Stripe Patterns on Surfaces (cover image)
  Felix Knoppel, Keenan Crane, Ulrich Pinkall, Peter Schroder
• Gaze-driven Video Re-editing
  Eakta Jain, Yaser Sheikh, Ariel Shamir, Jessica Hodgins
• Semantic Shape Editing Using Deformation Handles
  M. Ersin Yumer, Siddhartha Chaudhuri, Jessica Hodgins, Levent Burak Kara
• LinkEdit: Interactive Linkage Editing Using Symbolic Kinematics
  Moritz Bacher, Stelian Coros, Bernhard Thomaszewski
• Real-Time Style Transfer for Unlabeled Heterogeneous Human Motion
  Shihong Xia, Congyi Wang, Jinxiang Chai, Jessica Hodgins
• Design and Fabrication of Flexible Rod Meshes
  Jesus Perez, Bernhard Thomaszewski, Stelian Coros, Bernd Bickel, Jose Canabal, Robert Sumner, Miguel Otaduy
• A Perceptual Control Space for Garment Simulation
  Leonid Sigal, Moshe Mahler, Spencer Diaz, Kyna McIntosh, Elizabeth Carter, Timothy Richards, Jessica Hodgins

Recent articles feature work appearing at SIGGRAPH 2014:

Researchers at Carnegie Mellon University have created a way to manipulate objects in photos in three dimensions, allowing you to see all sides of formerly 2D objects. How is it done? Some might say there is dark magic afoot, but what’s really happening is far more interesting. Here’s how it’s done: an object is selected in an image, be it a chair, an origami crane, or a fireplug. The system matches the object with currently extant 3D models taken from various sources, and then, by connecting the models with the actual objects, they are able to simulate what the object would look like in the photograph. While this database of objects is obviously fairly limited, it does allow for some clever tricks including making taxi cabs in photos flip around to display their undercarriage and then zoom off into space.

Read more at New York Times, TechCrunch and R&D Magazine.

Keenan Crane will join the CMU Graphics Lab in 2015 as an Assistant Professor in the Computer Science Department and Robotics Institute. Keenan received a PhD from Caltech in 2013, as part of the Applied Geometry Lab and Multi-Res Modeling Group; he is currently an NSF Mathematical Sciences Postdoctoral Fellow at Columbia University. Keenan's research draws on insights from differential geometry and computer science to develop fast numerical algorithms and fundamental representations for real-world geometric data.  This work has been used in production at companies such as DreamWorks and Digital Domain, and has been covered by popular media including National Public Radio and Scientific American.  Hear Keenan talk about his work via the Everhart Lecture Series.

The CMU Graphics Lab will be presenting the following papers this summer at SIGGRAPH 2014

• Self-Refining Games using Player Analytics Matt Stanton, Ben Humberstron, Brandon Kase, James O'Brien (UC Berkeley), Kayvon Fatahalian, Adrien Treuille
• Extending the Graphics Pipeline with Adaptive, Multi-Rate Shading Yong He, Yan Gu, Kayvon Fatahalian
• 3D Object Manipulation in a Single Photograph using Stock 3D Models Natasha Kholgade, Tomas Simon, Alexei Efros (UC Berkeley), Yaser Sheikh
• Automatic Editing of Footage from Multiple Social Cameras Ido Arev, Hyun Soo Park, Yaser Sheikh, Jessica Hodgins, Ariel Shamir (Ido and Ariel are affiliated with: Interdisciplinary Center Herzliya, Disney Research Pittsburgh)

Doug James from Cornell University and Pat Hanrahan from Stanford University will visit CMU this Fall to receive the Katayanagi Prizes in Computer Science. Prof. James will give a distinguished lecture Sept. 12th, and Prof. Hanrahan will give a distinguished lecture on Sept 26th. Details will be announced shortly at http://www.cs.cmu.edu/~katayanagi/ Kayvon would like to add that he has been lucky to have some great advisors.