This is not a complete documentation of all our papers but a sub-set of works focused on developing stable correspondence and pose estimation. Thus far we have primarily focused on robustness and quality. We are now shifting the emphasis to speed.
A perennial problem in recovering 3-D models from images is repeated structures common in modern cities. The problem can be traced to the feature matcher which needs to match less distinctive features (permitting wide-baselines and avoiding broken sequences), while simultaneously avoiding incorrect matching of ambiguous repeated features. To meet this need, we develop RepMatch, an epipolar guided (assumes predominately camera motion) feature matcher that accommodates both wide-baselines and repeated structures. RepMatch is based on using RANSAC to guide the training of match consistency curves for differentiating true and false matches. By considering the set of all nearest-neighbour matches, RepMatch can procure very large numbers of matches over wide baselines. This in turn lends stability to pose estimation. RepMatch's performance compares favourably on standard datasets and enables more complete reconstructions of modern architectures.
A key challenge in feature correspondence is the difficulty in differentiating true and false matches at a local descriptor level. This forces adoption of strict similarity thresholds that discard many true matches. However, if analyzed at a global level, false matches are usually randomly scattered while true matches tend to be coherent (clustered around a few dominant motions), thus creating a coherence based separability constraint. This paper proposes a non-linear regression technique that can discover such a coherence based separability constraint from highly noisy matches and embed it into a correspondence likelihood model. Once computed, the model can filter the entire set of nearest neighbor matches (which typically contains over 90% false matches) for true matches. We integrate our technique into a full feature correspondence system which reliably generates large numbers of good quality correspondences over wide baselines where previous techniques provide few or no matches.
This is the direct predecessor to the CODE matching paper which uses the same formulation but is much faster.
This is another predecessor to the CODE paper. The CODE formulation means this paper can be implemented much faster. Maybe... someday, if we can get the time. =)