The RADIANCE lighting simulation and rendering system
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
The visible differences predictor: an algorithm for the assessment of image fidelity
Digital images and human vision
Visual navigation of large environments using textured clusters
I3D '95 Proceedings of the 1995 symposium on Interactive 3D graphics
A model of visual adaptation for realistic image synthesis
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
A framework for realistic image synthesis
Proceedings of the 24th annual conference on Computer graphics and interactive techniques
A multiscale model of adaptation and spatial vision for realistic image display
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Rendering with radiance: the art and science of lighting visualization
Rendering with radiance: the art and science of lighting visualization
A perceptually based physical error metric for realistic image synthesis
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Statistically optimized sampling for distributed ray tracing
SIGGRAPH '85 Proceedings of the 12th annual conference on Computer graphics and interactive techniques
Putting social sciences together again: an introduction to the volume
Dynamics in human and primate societies
Measuring and predicting visual fidelity
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Perception-guided global illumination solution for animation rendering
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Spatiotemporal sensitivity and visual attention for efficient rendering of dynamic environments
ACM Transactions on Graphics (TOG)
Selective quality rendering by exploiting human inattentional blindness: looking but not seeing
VRST '02 Proceedings of the ACM symposium on Virtual reality software and technology
Varying rendering fidelity by exploiting human change blindness
Proceedings of the 1st international conference on Computer graphics and interactive techniques in Australasia and South East Asia
A Visibility Matching Tone Reproduction Operator for High Dynamic Range Scenes
IEEE Transactions on Visualization and Computer Graphics
Tone Reproduction for Realistic Images
IEEE Computer Graphics and Applications
Comparing Real & Synthetic Scenes using Human Judgements of Lightness
Proceedings of the Eurographics Workshop on Rendering Techniques 2000
Perceptually driven simplification for interactive rendering
EGWR'01 Proceedings of the 12th Eurographics conference on Rendering
Human visual perception of region warping distortions
ACSC '06 Proceedings of the 29th Australasian Computer Science Conference - Volume 48
Proceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast Asia
Visual equivalence: towards a new standard for image fidelity
ACM SIGGRAPH 2007 papers
| Hi-index | 0.00 |
Despite the ready availability of modern high performance graphics cards, the complexity of the scenes being modelled and the realism required of the images means that rendering high fidelity computer images is still simply not possible in a reasonable, let alone real-time. Knowing that it is a human that will be looking at the resultant images can be exploited to significantly reduce the computation time required for high fidelity graphical images, for although the human visual system is good, it does have limitations. The key is knowing where the user will be looking in the image.This paper describes high level task maps and low level saliency maps. For a large number of applications, these visual attention models can indeed determine where the user will be looking in scene with high accuracy. This information is then used to selectively render different parts of a complex scene at different qualities. We show that viewers performing a known visual task within the environment consistently fail to notice the difference in rendering quality between benchmark high quality images and the selectively rendered images that were rendered at a fraction of the computational cost.