Keynote Talks
Optimizing light field camera designs (Mon 16:00)
Computational photography is pushing sophisticated computational thinking deeper into the imaging pipeline. For example, light field cameras record higher-dimensional data than conventional cameras, and enable new functionality, like depth inference, refocusing and correcting lens aberrations in post-processing. This talk will review the theory and intuition of light field camera design, and describe the resulting transformation of design considerations and opportunities in core subsystems: optics, sensors and processors. The development of such cameras opens the door to the use of light field cameras for computer vision and machine learning.
| Ren Ng is a faculty member in Electrical Engineering and Computer Science at the University of California, Berkeley. His research interests are in imaging, graphics and applied mathematics, focusing on the theory and engineering of computational imaging systems. In 2006, Ren founded Lytro, Inc., which commercialized his Ph.D. research and brought consumer light field cameras to market. Ren completed his Ph.D. in computer science at Stanford University. Awards include the ACM Doctoral Dissertation Award, Sloan Research Fellowship, Selwyn Medal from the Royal Photographic Society, MIT Tech Review's TR35 and Entrepreneur of the Year, Fast Company's 100 Most Creative People in Business, and Silicon Valley Journal's 40 under 40. |
Digital Avatars for All: Interactive Face and Hair (Tue 16:00)
Although realistic face/hair modeling and animation technologies have been widely employed in computer generated movies, it remains challenging to deploy them in consumer-level applications such as computer games, social networks and other interactive applications. The main difficulties come from the requirement of special equipment, sensitivity to daily environments, laborious manual work and high computational costs. In this talk, I will introduce our recent research on realistic face/hair modeling and animation, aiming at interactive applications and ordinary users. In particular, I will describe fully automatic approaches to real-time facial tracking and animation with a single web camera, methods for modeling hairs from images, and real-time algorithms for realistic hair simulation.
| Kun Zhou is a Cheung Kong Professor and the Director of the State Key Lab of CAD&CG at Zhejiang University. Earlier, he was a Lead Researcher of the Internet Graphics Group at Microsoft Research Asia. He received his BS and PhD degrees from Zhejiang University in 1997 and 2002, respectively. His research interests include geometry processing, photorealistic rendering, computer animation and GPU parallel computing. He is/was an associate editor of IEEE TVCG and ACM TOG, and serves on the editorial advisory board of IEEE Spectrum. He is a Fellow of IEEE. |
Schedule
Sunday, June 18
Monday, June 19
| 8:00-16:00 | Registration and Information Desk |
| 8:45-9:00 | Opening |
| 9:00-10:30 | Rendering is Everywhere (Chair: Pieter Peers) |
Minimal Warping: Planning Incremental Novel-view Synthesis (CGF)
Decomposing Single Images for Layered Photo Retouching (CGF)
Controlling and Sampling Visibility Information on the Image Plane (EI&I)
Single-Pass Stereoscopic GPU Ray Casting Using Re-Projection Layers (EI&I)
|
|
| 10:30-11:00 | Coffee Break |
| 11:00-12:30 | BRDFs and Illumination (Chair: Tim Weyrich) |
Real-Time Linear BRDF MIP-Mapping (CGF)
An Appearance Model for Textile Fibers (CGF)
Attribute preserving gamut mapping of measured BRDFs (CGF)
Ambient Dice (EI&I)
|
|
| 12:30-14:00 | Lunch |
| 14:00-15:30 | Lighting and Shading (Chair: Christian Lessig) |
Stochastic Light Culling for VPLs on GGX Microsurfaces (CGF)
Deep Shading: Convolutional Neural Networks for Screen-Space Shading (CGF)
VAO++: Practical Volumetric Ambient Occlusion for Games (EI&I)
Real-time solar exposure simulation in complex cities (CGF paper)
|
|
| 15:30-16:00 | Coffee Break |
| 16:00-17:00 | Keynote Talk (Ren Ng) |
| 18:00- | Social Event: Cruise with Light Dinner (Sponsored by Umbra) See map |
Tuesday, June 20
| 8:30-16:00 | Registration and Information Desk |
| 9:00-10:30 | Monte Carlo before Coffee (Chair: Matthias Zwicker) |
Variance and Convergence Analysis of Monte Carlo Line and Segment Sampling (CGF)
Frequency Based Radiance Cache for Rendering Animations (EI&I)
Temporal Coherence for Metropolis Light Transport (EI&I)
Extended Path Integral Formulation for Volumetric Transport (EI&I)
|
|
| 10:30-11:00 | Coffee Break |
| 11:00-12:30 | Monte Carlo after Coffee (Chair: Iliyan Georgiev) |
Practical Path Guiding for Efficient Light-transport Simulation (CGF)
Line Integration for Rendering Heterogeneous Emissive Volumes (CGF)
Local quasi-Monte Carlo exploration (EI&I)
Gradient-Domain Vertex Connection and Merging (EI&I)
|
|
| 12:30-14:00 | Lunch |
| 14:00-15:30 | Materials and Textures (Chair: Tamy Boubekeur) |
Bi-Layer textures: a Model for Synthesis and Deformation of Composite Textures (CGF)
Fiber-Level On-the-Fly Procedural Textiles (CGF)
Material Design in Augmented Reality with In-Situ Visual Feedback (EI&I)
sLayer: a System for Multi-Layered Material Sculpting (EI&I)
|
|
| 15:30-16:00 | Coffee Break |
| 16:00-17:00 | Keynote Talk (Kun Zhou) |
| 17:00-18:00 | Townhall Meeting |
| 19:00- | Conference Dinner (Restaurant Saaristo)
See map |
Wednesday, June 21
| 8:30-12:00 | Registration and Information Desk |
| 9:00-10:30 | Adding and Removing Noise (Chair: Fabrice Rousselle) |
Bayesian Collaborative Denoising for Monte Carlo Rendering (CGF)
Multiple Axis-Aligned Filters for Rendering of Combined Distribution Effects (CGF)
Noise Reduction on G-Buffers for Monte Carlo Filtering (CGF paper)
A Stochastic Film Grain Model for Resolution-Independent Rendering (CGF paper)
|
|
| 10:30-11:00 | Coffee Break |
| 11:00-12:30 | Geometric Techniques (Chair: Toshiya Hachisuka) |
Fast Hardware Construction and Refitting of Quantized Bounding Volume Hierarchies (CGF)
Area-Preserving Parametrizations for Spherical Ellipses (CGF)
A k-d Tree Designed for Motion Blur (EI&I)
|
|
| Closing |
Material Appearance Modeling Workshop (Sunday, June 18)
| 8:30-12:00 | Registration and Information Desk |
| 9:00-10:30 | New Models |
Appearance of Interfaced Lambertian Microfacets, using STD Distribution
Toward a Perceptually-Relevant Decomposition of Hazy Gloss
Image-Based Remapping of Material Appearance
|
|
| 10:30-11:00 | Coffee Break |
| 11:00-12:30 | Research Group Reports |
Material Appearance Research at U. Zaragoza
Material Appearance Research at NTNU
High-Quality Multi-Spectral Reflectance Acquisition with X-Rite TAC7
Towards Sparse and Multiplexed Acquisition of Material BTFs
|
|
| 12:30-14:00 | Lunch |
| 14:00-15:30 | Acquisition Issues |
Challenges in Appearance Capture and Predictive Modeling of Textile Materials
The Effects of Digital Cameras Optics and Electronics for Material Acquisition
Diffraction Prediction in HDR measurements
|
|
| 15:30-16:00 | Coffee Break |
| 16:00-17:00 | Evaluation and Discussion |
Experimental Analysis of BSDF Models
Towards a Dynamic BRDF Benchmark: Community Feedback
Closing Discussion
|