mlsanityData to 14 Oct 2026

Theoretical Analysis for Expectation-Maximization-Based Multi-Model 3D Registration

arXiv 2405.08991 ↗First posted 14 May 2024cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

We perform detailed theoretical analysis of an expectation-maximization-based algorithm recently proposed in for solving a variation of the 3D registration problem, named multi-model 3D registration. Despite having shown superior empirical results, did not theoretically justify the conditions under which the EM approach converges to the ground truth. In this project, we aim to close this gap by establishing such conditions. In particular, the analysis revolves around the usage of probabilistic tail bounds that are developed and applied in various instances throughout the course. The problem studied in this project stands as another example, different from those seen in the course, in which tail-bounds help advance our algorithmic understanding in a probabilistic way. We provide self-contained background materials on 3D Registration

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 38 references that are in the map. First posted on arXiv 14 May 2024.

Builds on

17 of 38 references.

References · 17

  1. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  2. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  3. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  4. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  5. 2022TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulationcited by 47
  6. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  7. 2021Planar Robot Casting with Real2Sim2Real Self-Supervised Learningcited by 39
  8. 2023FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projectioncited by 34
  9. 2017SegICP: Integrated Deep Semantic Segmentation and Pose Estimationcited by 29
  10. 2023DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classificationcited by 23
  11. 2020Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cablescited by 21
  12. 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transformscited by 17
5 more
  1. 20206-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNNcited by 13
  2. 2022ART/ATK: A research platform for assessing and mitigating the sim-to-real gap in robotics and autonomous vehicle engineeringcited by 10
  3. 2023APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistencycited by 9
  4. 2024GMKF: Generalized Moment Kalman Filter for Polynomial Systems with Arbitrary Noisecited by 8
  5. 2024Multi-Model 3D Registration: Finding Multiple Moving Objects in Cluttered Point Cloudscited by 7

Built on by

Not cited yet.