Recovering high dynamic range radiance maps from photographs
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
Noise Estimation from a Single Image
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Parallel Tracking and Mapping for Small AR Workspaces
ISMAR '07 Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Simulating Low-Cost Cameras for Augmented Reality Compositing
IEEE Transactions on Visualization and Computer Graphics
KinectFusion: Real-time dense surface mapping and tracking
ISMAR '11 Proceedings of the 2011 10th IEEE International Symposium on Mixed and Augmented Reality
DTAM: Dense tracking and mapping in real-time
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
High frame rate egomotion estimation
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Hi-index | 0.00 |
Higher frame-rates promise better tracking of rapid motion, but advanced real-time vision systems rarely exceed the standard 10–60Hz range, arguing that the computation required would be too great. Actually, increasing frame-rate is mitigated by reduced computational cost per frame in trackers which take advantage of prediction. Additionally, when we consider the physics of image formation, high frame-rate implies that the upper bound on shutter time is reduced, leading to less motion blur but more noise. So, putting these factors together, how are application-dependent performance requirements of accuracy, robustness and computational cost optimised as frame-rate varies? Using 3D camera tracking as our test problem, and analysing a fundamental dense whole image alignment approach, we open up a route to a systematic investigation via the careful synthesis of photorealistic video using ray-tracing of a detailed 3D scene, experimentally obtained photometric response and noise models, and rapid camera motions. Our multi-frame-rate, multi-resolution, multi-light-level dataset is based on tens of thousands of hours of CPU rendering time. Our experiments lead to quantitative conclusions about frame-rate selection and highlight the crucial role of full consideration of physical image formation in pushing tracking performance.