mlsanityData to 14 Oct 2026

HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation

arXiv 2609.21597 ↗First posted 18 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Monocular 6-DoF pose estimation of non-cooperative targets is important for on-orbit servicing and debris removal. A single-image estimator can confuse near-symmetric spacecraft orientations, and tracking can preserve an incorrect pose. We present Hypothesis-Anchored Tracking (HAT), a causal framework that uses inter-frame motion to select among competing CAD-based pose hypotheses before alignment and fusion. Rather than independently choosing the highest-scoring hypothesis in each image, HAT retains competing orientation histories and selects a pose to anchor the relative trajectory estimated by monocular SLAM. Sparse anchors and pose fusion provide per-frame estimates after initialization without revising past outputs. The method requires only a calibrated RGB sequence, a metric CAD model, and target image regions, which can be supplied by detection or segmentation. The pretrained pose and SLAM networks require no target-specific training or fine-tuning. We evaluate two versions, Mega-HAT and Pico-HAT, using MegaPose and PicoPose, on SPARK-2024, SwissCube and SHIRT, with YCB-Video assessing performance outside the space domain. Using one temporal configuration per method, the arithmetic means of the four dataset-wise comparisons show 9.4% lower mean pose error and 3.76 times the sustained input FPS for Mega-HAT relative to independent MegaPose, and 23.9% lower mean pose error and 2.42 times the FPS for Pico-HAT relative to independent PicoPose. Mega-HAT ablations on SPARK and an offline reference examine component contributions and the effect of revising past estimates.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 18 Sep 2026.

Builds on

20 of 27 references.

References · 20

  1. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  2. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  3. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  4. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  5. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 87
  6. 2019Satellite Pose Estimation Challenge: Dataset, Competition Design and Resultscited by 62
  7. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  8. 2021SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gapcited by 57
  9. 2019Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinementcited by 56
  10. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  11. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  12. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 33
8 more
  1. 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
  2. 2021SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real Worldcited by 19
  3. 2022Adaptive Neural Network-based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraftcited by 16
  4. 2023SPADES: A Realistic Spacecraft Pose Estimation Dataset using Event Sensingcited by 13
  5. 2021ChiNet: Deep Recurrent Convolutional Learning for Multimodal Spacecraft Pose Estimationcited by 11
  6. 2025PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimationcited by 6
  7. 2025RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Trackingcited by 6
  8. 2025Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimationcited by 2

Built on by

Not cited yet.