Appearance Acquisition for Digital 3D Content Creation

Appearance Acquisition for Digital 3D Content Creation

Andreas Geiger via YouTube Direct link

Generalizable neural representations

34 of 35

34 of 35

Generalizable neural representations

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Appearance Acquisition for Digital 3D Content Creation

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Geometry + Material
  3. 3 Image-based appearance acquisition
  4. 4 RGBD reconstructions
  5. 5 Projective texture mapping
  6. 6 Previous works
  7. 7 Our approach
  8. 8 Observations
  9. 9 Similarity: coherence
  10. 10 Similarity: completeness + coherence
  11. 11 Consistency
  12. 12 Patch-base energy function
  13. 13 Multi-scale optimization
  14. 14 Comparison against single-view selection
  15. 15 Acquisition setup
  16. 16 Learning-based multi-view stereo
  17. 17 SVBRDF prediction
  18. 18 Geometry reconstruction
  19. 19 Volumetric representations
  20. 20 Relightable reconstructions
  21. 21 Joint view synthesis and relighting
  22. 22 Mobile phone captures with flashlight
  23. 23 Discretized volume rendering
  24. 24 Learning deep reflectance volumes
  25. 25 Loss functions
  26. 26 Comparison to mesh-based methods
  27. 27 Comparison on synthetic data
  28. 28 Environment map rendering
  29. 29 Physically-accurate volume rendering
  30. 30 More results
  31. 31 Integration with a physically-based rendere
  32. 32 Sparse geometry and BRDF acquisition
  33. 33 Neural representations for scenes
  34. 34 Generalizable neural representations
  35. 35 Integration with traditional rendering

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.