mlsanityData to 14 Oct 2026

Parallel Sampling of Diffusion Models on SO(3)

arXiv 2507.10347 ↗First posted 14 Jul 2025cs.LGcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper, we design an algorithm to accelerate the diffusion process on the SO(3) manifold. The inherently sequential nature of diffusion models necessitates substantial time for denoising perturbed data. To overcome this limitation, we proposed to adapt the numerical Picard iteration for the SO(3) space. We demonstrate our algorithm on an existing method that employs diffusion models to address the pose ambiguity problem. Moreover, we show that this acceleration advantage occurs without any measurable degradation in task reward. The experiments reveal that our algorithm achieves a speed-up of up to 4.9×, significantly reducing the latency for generating a single sample.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 16 of its 23 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

16 of 23 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Parallel Sampling of Diffusion Models25 May
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 10

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  4. 2018A micro Lie theory for state estimation in roboticscited by 124
  5. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  6. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  7. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  8. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  9. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  10. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Spacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
  2. 2024Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
  3. 2024Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
  4. 2025Parallel Sampling via Autospeculation
  5. 2024Accelerating Convergence of Score-Based Diffusion Models, Provably
  6. 2025Faster Diffusion Models via Higher-Order Approximation
  7. 2023A Geometric Perspective on Diffusion Models
  8. 2026Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling