Dense Segmentation-aware Descriptors

Abstract : In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor's center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptors that are densely computable, invariant to scaling and rotation, and robust to background changes. We apply our approach to standard benchmarks on large displacement motion estimation using SIFT-flow and wide-baseline stereo, systematically demonstrating that the introduction of segmentation yields clear improvements.
Document type :
Conference papers
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.inria.fr/hal-00856023
Contributor : Eduard Trulls Fortuny <>
Submitted on : Friday, August 30, 2013 - 2:37:00 PM
Last modification on : Thursday, February 7, 2019 - 5:29:21 PM
Long-term archiving on : Thursday, April 6, 2017 - 11:02:14 AM

File

cvpr13-final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00856023, version 1

Collections

Citation

Eduard Trulls, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer. Dense Segmentation-aware Descriptors. Computer Vision and Pattern Recognition, Jun 2013, Portland, Oregon, United States. ⟨hal-00856023⟩

Share

Metrics

Record views

326

Files downloads

514