Motion Segmentation by Exploiting Complementary Geometric Models

Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty. Even when we are confronted with a general scene-motion, the fundamental matrix approach as a model for motion segmentation still suffers from several defects, which we discuss in this paper... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Motion Segmentation Hopkins155 MVC Classification Error 0.31 # 1
Motion Segmentation KT3DMoSeg MultiViewClustering Error 7.92 # 1
Motion Segmentation MTPV62 MVC Classification Error 0.65 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet