mlsanityData to 14 Oct 2026

Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion

arXiv 2603.10584 ↗First posted 11 Mar 2026cs.CV cs.ROcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based methods. By shifting computational burden from inference to finetuning, our approach enables efficient and robust 3D perception under real-world latency constraints. Marigold-SSD achieves significantly faster inference with a training cost of only 4.5 GPU days. We evaluate our method across four indoor and two outdoor benchmarks, demonstrating strong cross-domain generalization and zero-shot performance compared to existing depth completion approaches. Our approach significantly narrows the efficiency gap between diffusion-based and discriminative models. Finally, we challenge common evaluation protocols by analyzing performance under varying input sparsity levels. Page: https://dtu-pas.github.io/marigold-ssd/

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 71 of its 89 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

71 of 89 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers8 Oct
  2. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation22 Jan
  3. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion18 Dec
  4. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation27 Nov
  5. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think17 Sep
  6. 2024PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage13 Sep
  7. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion20 Mar
  8. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image18 Mar

Other references · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2022Flow Matching for Generative Modelingcited by 5,702
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2017Neural Discrete Representation Learningcited by 4,712
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  12. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
38 more
  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  3. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  5. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  6. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  7. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  8. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  9. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  10. 2020Virtual KITTI 2cited by 353
  11. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  12. 2017Sparsity Invariant CNNscited by 326
  13. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  14. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  15. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
  16. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  17. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 166
  18. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  19. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 138
  20. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  21. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 110
  22. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  23. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  24. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 93
  25. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 89
  26. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  27. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  28. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  29. 2024Bilateral Propagation Network for Depth Completioncited by 60
  30. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 49
  31. 2024Tri-Perspective View Decomposition for Geometry-Aware Depth Completioncited by 42
  32. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  33. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  34. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 30
  35. 2024BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimationcited by 28
  36. 2022Sparsity Agnostic Depth Completioncited by 27
  37. 2024OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterationscited by 24
  38. 2022SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completioncited by 23

50 most cited of 63 All 63 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior
  2. 2025DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulation
  3. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
  4. 2024GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
  5. 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
  6. 2026Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
  7. 2026Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
  8. 2025GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation