Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 188

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Open access
Jampani, Varun, Kiefel, Martin, Gehler, Peter V.·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be used in several diverse applications. First, we demonstrate the use in applications where single filter applications are desired for runtime reasons. Further, we show how this algorithm can be used to learn the pairwise potentials in densely connected conditional random fields and apply these to different image segmentation tasks. Finally, we introduce layers of bilateral filters in CNNs and propose bilateral neural networks for the use of highdimensional sparse data. This view provides new ways to encode model structure into network architectures. A diverse set of experiments empirically validates the usage of general forms of filters.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2016.482

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 9 references

Research works printed but not linked: 39

  1. 10.1109/CVPR.2015.7298595 · DOI
  2. krähenbühl, 2013, Parameter learning and convergent inference for dense random fields, International Conference on Machine Learning (ICML), 513
  3. krähenbühl, 2011, Efficient inference in fully connected CRFs with Gaussianedge potentials, Neural Information and Processing Systems (NIPS)
  4. kopf, 2007, Joint bilateral upsampling, ACM Transactions on Graphics (TOG), 26, 96, 10.1145/1276377.1276497 · DOI · Paper page
  5. paris, 2009, Bilat-eral filtering Theory and applications
  6. paris, 2006, A fast approximation of the bilateral filter using a signal processing approach, European Conference on Computer Vision (ECCV), 568
  7. milanfar, 2011, A tour of modern image filtering, IEEE Signal Processing Magazine, 2
  8. li, 2014, Mean-field networks, ICML Work-shop on Learning Tractable Probabilistic Models
  9. 10.1145/2647868.2654889 · DOI · Paper page
  10. jaderberg, 2015, Spatial transformer networks, Neural Information Processing Systems (NIPS)
  11. kiefel, 2014, Human pose estimation with fields of parts, European Conference on Computer Vision (ECCV), 331
  12. 10.1111/j.1467-8659.2009.01645.x · DOI · Paper page
  13. 0, Google Image
  14. 10.1109/ICCV.2015.66 · DOI
  15. graham, 2014, Spatially-sparse convolutional neural networks
  16. 10.1145/2185520.2185529 · DOI · Paper page
  17. 10.5244/C.29.150 · DOI · Paper page
  18. ionescu, 2015, Matrix back-propagation for deep networks with structured layers, International Conference on Computer Vision (ICCV)
  19. 10.1109/ICIP.2007.4378957 · DOI
  20. bell, 2014, Intrinsic images in the wild, ACM Transactions on Graphics (TOG), 33, 159, 10.1145/2601097.2601206 · DOI · Paper page
  21. bruna, 2013, Spectral networks and locally connected networks on graphs
  22. 10.1109/CVPR.2013.217 · doi:10.1109/cvpr.2013.217
  23. 10.1109/CVPR.2012.6248110 · DOI · Paper page
  24. 10.1109/TPAMI.2013.31 · DOI
  25. eigen, 2014, Depth map prediction from a single image using a multi-scale deep network, Neural Information Processing Systems (NIPS), 2366
  26. everingham, 2012, The PASCAL voc2012 Challenge Results
  27. aurich, 1995, Non-linear Gaussian filters performing edge preserving diffusion, DAGM, 538
  28. adams, 2009, Gaussiankd-trees for fast high-dimensional filtering, ACM Transactions on Graphics (TOG), 28, 21, 10.1145/1531326.1531327 · DOI · Paper page
  29. bache, 2013, UCI Machine Learning Repository
  30. 10.1109/CVPR.2005.176 · DOI
  31. 10.1109/CVPR.2015.7299076 · DOI
  32. 10.1109/TPAMI.2002.1008390 · DOI · Paper page
  33. barron, 2015, The Fast Bilateral Solver, ArXiv e-prints
  34. vineet, 2013, Posefield: An efficient mean-field based method for joint estimation of human pose, segmentation and depth, EMMCVPR
  35. 10.1109/CVPR.2010.5539957 · DOI · Paper page
  36. 10.1007/978-3-642-33715-4_3 · DOI
  37. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, CoRR abs/1409 1556
  38. 10.1109/TIP.2006.888330 · DOI · Paper page
  39. 10.1109/CVPR.2013.317 · DOI

Cited by

See all 188

Metadata

Authors
Jampani, V., Kiefel, M., & Gehler, P. V.
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
4452-4461
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2264432461
Cited by
188
References
9
FWCI
7.87
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks. https://app.cochat.ai/papers/10.1109/cvpr.2016.482
The paper
Jampani, V., Kiefel, M., & Gehler, P. V. (2016). Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.482

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.