mlsanityData to 14 Oct 2026

Taking a Deeper Look at the Inverse Compositional Algorithm

arXiv 1812.06861 ↗First posted 17 Dec 2018cs.CV cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 4; 2023: 3; 2024: 1; 2025: 0; 2026: 2.

20 papers.

Sort:

By area:

  1. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  2. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  3. 2022Theseus: A Library for Differentiable Nonlinear Optimizationcited by 65
  4. 2024GeoCalib: Learning Single-image Calibration with Geometric Optimizationcited by 52
  5. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  6. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  7. 2021Deep Lucas-Kanade Homography for Multimodal Image Alignmentcited by 38
  8. 2022Satellite Image Based Cross-view Localization for Autonomous Vehiclecited by 19
  9. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  10. 2021Learning to Fit Morphable Modelscited by 16
  11. 2022Residual Aligner Networkcited by 10
  12. 2021VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enoughcited by 9
8 more
  1. 2023PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstructioncited by 7
  2. 2021View Birdification in the Crowd: Ground-Plane Localization from Perceived Movementscited by 4
  3. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
  4. 2022Reuse your features: unifying retrieval and feature-metric alignmentcited by 1
  5. 2026HomoFM: Deep Homography Estimation with Flow Matchingcited by 1
  6. 2026Learn2Splat: Extending the Horizon of Learned 3DGS Optimizationcited by 1
  7. 2021SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)cited by 0
  8. 2021Probabilistic Tracking with Deep Factorscited by 0