1 / 27

Scheduling Level of Detail with guaranteed Quality and Cost

Scheduling Level of Detail with guaranteed Quality and Cost. W. Pasman, F. W. Jansen Delft University of Technology. UbiCom mobile AR. Latency Layering • Optical AR -> Low latency (10ms target for our system) on low-power headset -> Latency layering. Low-Latency Rendering.

berk-neal
Download Presentation

Scheduling Level of Detail with guaranteed Quality and Cost

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Scheduling Level of Detail with guaranteed Quality and Cost W. Pasman, F. W. Jansen Delft University of Technology

  2. UbiCom mobile AR

  3. Latency Layering • Optical AR -> Low latency (10ms target for our system) on low-power headset -> Latency layering

  4. Low-Latency Rendering • Render just ahead of rasterbeam •Voodoo2 3D game card • measured latency 8.5ms

  5. Dynamic Simplification Dynamic LoD generation in backbone Maximize perf/cost ratio in headset.

  6. Mathematical model • Estimate link and CPU load, memory usage, lifetime of objects, etc • Est screenspace error derived from geometric distortions D=0.001 R=1m

  7. Overview Mathematical model only for single objects -> complex scenes require resource scheduling • Accuracy Curves • VRML Integration • Measurements

  8. Scheduling of resources Funkhouser,Séquin (1992), Mason,Blake (1997) Goal: maximize benefit within a cost budget.

  9. Mason showed this is NP complete.. - Iterative approx giving in worst case half the maximum possible quality - Quality only known after iteration - Only feedback loop with application possible

  10. Accuracy Curves

  11. Each node in scene graph is assigned a curve: Accuracy curve • required resources as function of accuracy target • monotonically increasing. R->#polygons

  12. Measurement of geometric distortion d as function of number of polygons n d~ C/n. Accuracy a =1/d Resource usage r = K a + R0 -> piecewise linear function

  13. Propagating accuracy curves Leaf nodes: accuracy curve from (1) mathematical model or (2) measurements Other nodes: propagate curve upwards through scenegraph

  14. LoD node behaviour Resource Usage

  15. Different end points curve 2 Resource usage incorrect extension curve 1 incorrect minimum 20 50 Accuracy

  16. Complexity Target Accuracy -> Resources required Idem R -> A (so not NP-complete)

  17. Optimizing curve updates Upto now: screenspace error=visual accuracy Refresh required if user moves Optimizations: Determine range where a curve is ‘accurate enough’ as long as viewer is within the range. (2) Visual accuracy is derived from geometric distortion - which is viewpoint independent geometric accuracy object radius Relative acc =

  18. Using relative accuracy curves Slight changes in algorithms: • grouping -> 'object' diameter changes. • Conversion to visual accuracy needed. Group's bbox is much closer to viewer than the individual bboxes -> switch to absolute accuracy at reasonable distance.

  19. VRML Integration

  20. ConicRange Accuracy curves & simplified objects: valid only in part of space. Efficient checking. d

  21. Imposter nodes Replace children with image. Automatic refresh & calc of accuracy curve SimpleImposter { MFNode children [ ] SFVec2f size 2 2 SFBool autosize true SFVec3f center 0 0 0 SFBool autocenter true }

  22. LOD LOD picks valid level requiring least resources

  23. Measurements

  24. Prototype limitations -> simple testscene Target #polygons, accuracy Measure also SNR

  25. Constant polygon budget Constant accuracy target

  26. Conclusions • Efficient scheduling of resources • Fits all simplification methods • Rendering to target quality or budget driven • Comes close to budget, never exceeds it. • Hierarchical approach fits with VRML • Many optimization possibilities

  27. Future work • Limited prototype: part of UbiCom AR system • Many representations can change at once. This causes peak datarates. • Extension to multiple resources • Conic ranges quickly degenerate • Animated objects

More Related