Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
lib:09b2891d7df99385 (v1.0.0)
Authors: Pia Bideau,Aruni RoyChowdhury,Rakesh R. Menon,Erik Learned-Miller
Where published: CVPR 2018 6
Document: PDF DOI
Abstract URL: http://openaccess.thecvf.com/content_cvpr_2018/html/Bideau_The_Best_of_CVPR_2018_paper.html
Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid motion flow based on classical perspective projection constraints. We then combine piecewise rigid motions into complex deformable and articulated objects, guided by semantic segmentation from CNNs and a second ``object-level" statistical model. This combination of classical geometric knowledge combined with the pattern recognition abilities of CNNs yields excellent performance on a wide range of motion segmentation benchmarks, from complex geometric scenes to camouflaged animals.
Where published: CVPR 2018 6
Document: PDF DOI
Abstract URL: http://openaccess.thecvf.com/content_cvpr_2018/html/Bideau_The_Best_of_CVPR_2018_paper.html
Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid motion flow based on classical perspective projection constraints. We then combine piecewise rigid motions into complex deformable and articulated objects, guided by semantic segmentation from CNNs and a second ``object-level" statistical model. This combination of classical geometric knowledge combined with the pattern recognition abilities of CNNs yields excellent performance on a wide range of motion segmentation benchmarks, from complex geometric scenes to camouflaged animals.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)