mlsanityData to 14 Oct 2026

FPG-NAS: FLOPs-Aware Gated Differentiable Neural Architecture Search for Efficient 6DoF Pose Estimation

arXiv 2508.03618 ↗First posted 5 Aug 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce FPG-NAS, a FLOPs-aware Gated Differentiable Neural Architecture Search framework for efficient 6DoF object pose estimation. Estimating 3D rotation and translation from a single image has been widely investigated yet remains computationally demanding, limiting applicability in resource-constrained scenarios. FPG-NAS addresses this by proposing a specialized differentiable NAS approach for 6DoF pose estimation, featuring a task-specific search space and a differentiable gating mechanism that enables discrete multi-candidate operator selection, thus improving architectural diversity. Additionally, a FLOPs regularization term ensures a balanced trade-off between accuracy and efficiency. The framework explores a vast search space of approximately 10textsuperscript92 possible architectures. Experiments on the LINEMOD and SPEED+ datasets demonstrate that FPG-NAS-derived models outperform previous methods under strict FLOPs constraints. To the best of our knowledge, FPG-NAS is the first differentiable NAS framework specifically designed for 6DoF object pose estimation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 5 Aug 2025.

Builds on

35 of 45 references.

References · 35

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2017Mixed Precision Trainingcited by 1,156
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  6. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  7. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  8. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  9. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  10. 2019GhostNet: More Features from Cheap Operationscited by 410
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
23 more
  1. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  2. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  3. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  4. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  5. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  6. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  7. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  8. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  9. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  10. 2021SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gapcited by 57
  11. 2020EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approachcited by 46
  12. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  13. 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
  14. 2021GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarizationcited by 29
  15. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  16. 2022HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillationcited by 11
  17. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictionscited by 9
  18. 2023Improving Differentiable Architecture Search via Self-Distillationcited by 6
  19. 2024Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversitycited by 5
  20. 2025Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimationcited by 5
  21. 2023Hardware Aware Evolutionary Neural Architecture Search using Representation Similarity Metriccited by 3
  22. 2023Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularizationcited by 2
  23. 2025Regularizing Differentiable Architecture Search with Smooth Activationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1