Selective image rendering based on an improved perceptual saliency model
Computer graphics is becoming more and more important in film and game industries. However, photorealistic image rendering is still very time consuming. To reduce the rendering cost has always been a difficult task for researchers. Visual attention guided rendering is one of the most important areas...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/43959 |
| _version_ | 1811692477665509376 |
|---|---|
| author | Xu, Yadong. |
| author2 | Lin Weisi |
| author_facet | Lin Weisi Xu, Yadong. |
| author_sort | Xu, Yadong. |
| collection | NTU |
| description | Computer graphics is becoming more and more important in film and game industries. However, photorealistic image rendering is still very time consuming. To reduce the rendering cost has always been a difficult task for researchers. Visual attention guided rendering is one of the most important areas of selective rendering. This project is to develop a perceptual saliency model and implement it as a selective rendering scheme which generates better quality images compared to an existing visual attention based rendering with the same amount of rendering cost. Our implementation is based on Physically Based Rendering Tool (PBRT). A blended saliency map which contains visual attention information and local sample contrast information is proposed and it guides the sampling process of the selective rending scheme. Integrating local sample contrast information into visual attention rendering in our experiment has demonstrated a better result than pure visual attention based rendering. |
| first_indexed | 2024-10-01T06:36:25Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/43959 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:36:25Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/439592023-03-03T20:40:01Z Selective image rendering based on an improved perceptual saliency model Xu, Yadong. Lin Weisi School of Computer Engineering Centre for Multimedia and Network Technology DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics Computer graphics is becoming more and more important in film and game industries. However, photorealistic image rendering is still very time consuming. To reduce the rendering cost has always been a difficult task for researchers. Visual attention guided rendering is one of the most important areas of selective rendering. This project is to develop a perceptual saliency model and implement it as a selective rendering scheme which generates better quality images compared to an existing visual attention based rendering with the same amount of rendering cost. Our implementation is based on Physically Based Rendering Tool (PBRT). A blended saliency map which contains visual attention information and local sample contrast information is proposed and it guides the sampling process of the selective rending scheme. Integrating local sample contrast information into visual attention rendering in our experiment has demonstrated a better result than pure visual attention based rendering. Bachelor of Engineering (Computer Engineering) 2011-05-16T04:52:19Z 2011-05-16T04:52:19Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/43959 en Nanyang Technological University 53 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics Xu, Yadong. Selective image rendering based on an improved perceptual saliency model |
| title | Selective image rendering based on an improved perceptual saliency model |
| title_full | Selective image rendering based on an improved perceptual saliency model |
| title_fullStr | Selective image rendering based on an improved perceptual saliency model |
| title_full_unstemmed | Selective image rendering based on an improved perceptual saliency model |
| title_short | Selective image rendering based on an improved perceptual saliency model |
| title_sort | selective image rendering based on an improved perceptual saliency model |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics |
| url | http://hdl.handle.net/10356/43959 |
| work_keys_str_mv | AT xuyadong selectiveimagerenderingbasedonanimprovedperceptualsaliencymodel |