mlsanityData to 14 Oct 2026

Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images

arXiv 2508.02323 ↗First posted 4 Aug 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D ground truth or multi-view supervision. We propose to leverage pre-trained 2D diffusion models and depth prediction models to generate synthetic scene geometry from a single image. This can then be used to distill a feed-forward scene reconstruction model. Our experiments on the challenging KITTI-360 and Waymo datasets demonstrate that our method matches or outperforms state-of-the-art baselines that use multi-view supervision, and offers unique advantages, for example regarding dynamic scenes.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 63 of its 71 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

63 of 71 references.

References · 63

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  10. 2021Vision Transformers for Dense Predictioncited by 1,803
  11. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
38 more
  1. 2024Depth Anything V2cited by 1,422
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  5. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  7. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  8. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  9. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  10. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  11. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  12. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  13. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  14. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  15. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  16. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  17. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  18. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  19. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  20. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  21. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  22. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  23. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  24. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  25. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  26. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  27. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  28. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  29. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  30. 2023Scene as Occupancycited by 209
  31. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  32. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  33. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  34. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  35. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  36. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 123
  37. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  38. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Stepper: Stepwise Immersive Scene Generation with Multiview Panoramascited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
  2. 2026Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
  3. 2025DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
  4. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
  5. 2024Coherent 3D Scene Diffusion From a Single RGB Image
  6. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
  7. 2024FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation
  8. 2026Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation