arXiv (Cornell University)· 2012· Preprint
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- 2,980citations
- 2012year
Short summary
A new approximate inference algorithm enables efficient computation for fully connected Conditional Random Fields (CRFs) with Gaussian edge potentials, allowing dense pixel-level connections in image segmentation.
AI-generated from the title and abstract; the full text is not read.
Key points
- Developed an efficient approximate inference algorithm for fully connected CRFs.
- The algorithm supports Gaussian kernel-based pairwise edge potentials.
- Enables dense pixel-level connectivity in image segmentation models.
- Dense connectivity demonstrably improves segmentation accuracy.
AI-generated from the title and abstract; the full text is not read.
Abstract
Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experiments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.
The authors' abstract, as published at the source. arXiv (Cornell University), 2012 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering