Pith. sign in

REVIEW

Decoupling Features and Coordinates for Few-shot RGB Relocalization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.11534 v4 pith:MRLR2NKU submitted 2019-11-26 cs.CV

Decoupling Features and Coordinates for Few-shot RGB Relocalization

classification cs.CV
keywords featurecoordinatescenefew-shotregressionrelocalizationadaptionapproach
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art approaches, however, can hardly support such few-shot scene adaption due to the entangling of image feature extraction and scene coordinate regression. To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately. Our key insight is that feature encoder used for coordinate regression should be learned by removing the distracting factor of coordinate systems, such that feature encoder is learned from multiple scenes for general feature representation and more important, view-insensitive capability. With this feature prior, and combined with a coordinate regressor, few-shot observations in a new scene are much easier to connect with the 3D world than the one with existing integrated solution. Experiments have shown the superiority of our approach compared to the state-of-the-art methods, producing higher accuracy on several scenes with diverse visual appearance and viewpoint distribution.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.