1 / 32

Structure Recovery by Part Assembly

Structure Recovery by Part Assembly. Chao- Hui Shen 1 Hongbo Fu 2 Kang Chen 1 Shi-Min Hu 1. 1 Tsinghua University 2 City University of Hong Kong. Background. Consumer level scanning devices Capture both RGB and depth Reconstruction is challenging Low resolution Noise

barbie
Download Presentation

Structure Recovery by Part Assembly

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. Structure Recovery by Part Assembly Chao-Hui Shen1Hongbo Fu2 Kang Chen1 Shi-Min Hu1 1Tsinghua University 2City University of Hong Kong

  2. Background • Consumer level scanning devices • Capture both RGB and depth • Reconstruction is challenging • Low resolution • Noise • Missing data • …

  3. Example-based Scan Completion • Global-to-local and top-down [Kraevoyand Sheffer2005; Paulyet al. 2005] • Rely on the availability of suitable template model • However … shape retrieval No suitable model!

  4. Assembly-based 3D Modeling • Data-drive suggestion and interaction [Chaudhuri and Koltun 2010; Chaudhuri et al. 2011] • Retrieve suitable parts to match user intent • Aim to support open-ended 3D modeling • Quite different goal from ours • Automatic shape synthesis by part composition [Kalogerakis et al. 2012; Jain et al. 2012; Xu et al. 2012] • Result in database that grows exponentially • Significantly enlarge the existing database • But make storage and retrieval challenging

  5. Our solution: Recover the Structure by Part Assembly • Structure recovery instead of geometry reconstruction • Do NOT prepare a large database • Retrieve and assemble suitable parts on the fly

  6. Problem Setup Session: Acquiring and Synthesizing Indoor Scenes An Interactive Approach to Semantic Modeling of Indoor Scenes with an RGBD Camera [Shao et al. 2012] A Search-Classify Approach for Cluttered Indoor Scene Understanding [Nan et al. 2012] Acquiring 3D Indoor Environments with Variability and Repetition [Kim et al. 2012] Goal: Recover high-level structure Assembly close to geometry Point cloud + Image (Single view) …… …… Pre-segmented Repository Models (Parts + Labels) Input Output

  7. Observations • Directly searching is computationally prohibitive • Need a quick way to explore meaningful structures guided by: • Spatial layout of the parts in the repository models • Acquired data

  8. Observations • Complementary characteristics of point cloud & image 3D, more accurate cues for geometry & structure Lack depth information Capture the complete object Incomplete and noisy

  9. Algorithm Overview …… Candidate Parts Selection Structure Composition Part Conjoining

  10. Algorithm Overview …… Candidate Parts Selection Structure Composition Part Conjoining

  11. Candidate Parts Selection • Goal: select a small set of candidates for each category • Achieved by retrieving parts that fit well some regions

  12. Straightforward Solution • Search for the best-fit parts over the entire domain • Disregards the semantics associated with each part and the interaction between different parts Unlikely to produce good results! X X X X X X X X

  13. Key Fact • Man-made objects lie in a low dimensional space • Defined with respect to the relative sizes and positions of shape parts [Ovsjanikov et al. 2011] • Employ 3D repository model as a global context • Globally align the models with the input scan first Search in a 3D offset window around the part

  14. Part Matching Scheme Geometric fidelity score edge map 3D 2D (part contour) Geometric contribution score Total matching score (2D field) 3D offset window

  15. Candidate Parts • Select top K parts with highest score for each category …… Seat …… Back …… Arm …… Front leg …… …… …… …… …… …… ……

  16. Algorithm Overview …… Candidate Parts Selection Structure Composition Part Conjoining

  17. Structure Composition • Goal: compose the underlying structure by identifying a subset of candidate parts

  18. Constraints for Promising Compositions    having high score no isolated parts minimized intersection    Geometric fidelity Proximity Overlap

  19. Search and Evaluate • Search for promising compositions under constraints • Globally Evaluate the compositions …… optimal composition total geometry contribution average geometry fidelity of parts total geometry fidelity

  20. Algorithm Overview …… Candidate Parts Selection Structure Composition Part Conjoining

  21. Part Conjoining • Problem: the parts are loosely placed together • Goal: generate a consistent & complete model

  22. Identification of Contact Points • Refer to their parent models [Jain et al. 2012]

  23. Matching of Contact Points • Greedily match nearby contact points • Generate auxiliary contact points when necessary auxiliary contact points

  24. Global Optimization • Adjust the sizes {} and positions {} of parts • Make matched point as close as possible • Contact enforcement • Shape preserving • Global optimization j i identity scale transformed contact points

  25. Results: Chairs • 70 repository models, 11 part categories

  26. Results: Tables • 61 repository models, 4 part categories

  27. Results: Bicycles • 38 repository models, 9 part categories

  28. Results: Airplanes • 70 repository models, 6 part categories

  29. Results: Creating New Structures

  30. Results: Impact of Dataset Randomly picking some repository models input data

  31. Summary • A bottom-up structure recovery approach • Effectively reuse limited repository models • Automatically compose new structure • Handle single-view inputs by the Kinect system • Future work • Multi-view inputs • Include style/functional constraints • Recover Indoor scenes

  32. Thank you! Project Page: http://cg.cs.tsinghua.edu.cn/StructureRecovery

More Related