mlsanityData to 7 Oct 2026

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

arXiv 2406.04343 ↗First posted 6 Jun 2024cs.CVcited by 113

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and extend it to a full 3D shape and appearance reconstructor. For efficiency, we base this extension on feed-forward Gaussian Splatting. Specifically, we predict a first layer of 3D Gaussians at the predicted depth, and then add additional layers of Gaussians that are offset in space, allowing the model to complete the reconstruction behind occlusions and truncations. Flash3D is very efficient, trainable on a single GPU in a day, and thus accessible to most researchers. It achieves state-of-the-art results when trained and tested on RealEstate10k. When transferred to unseen datasets like NYU it outperforms competitors by a large margin. More impressively, when transferred to KITTI, Flash3D achieves better PSNR than methods trained specifically on that dataset. In some instances, it even outperforms recent methods that use multiple views as input. Code, models, demo, and more results are available at https://www.robots.ox.ac.uk/~vgg/research/flash3d/.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). Builds on 85 of its 110 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

85 of 110 references.

References · 85

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  11. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
38 more
  1. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  2. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  3. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  4. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  6. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  7. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  8. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  9. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  11. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  13. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  14. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  15. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  16. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  17. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  18. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  19. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  20. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  21. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  22. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  23. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  24. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  25. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  26. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  27. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  28. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  29. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  30. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  31. 2022Novel View Synthesis with Diffusion Modelscited by 299
  32. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  33. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 278
  34. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  35. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  36. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  37. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  38. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 27; 2025: 55; 2026: 31.

113 papers.

Sort:

By area:

  1. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  2. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  3. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  4. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  5. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  6. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  7. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  8. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  9. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  10. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  11. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  12. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
38 more
  1. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  2. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  3. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 53
  4. 2024GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understandingcited by 46
  5. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  6. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  7. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 37
  8. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 36
  9. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 35
  10. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generationcited by 33
  11. 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
  12. 2024Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstructioncited by 32
  13. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Modelcited by 31
  14. 2024DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Drivingcited by 27
  15. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  16. 2024Splatter-360: Generalizable 360circ Gaussian Splatting for Wide-baseline Panoramic Imagescited by 23
  17. 2024PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splattingcited by 23
  18. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  19. 2025EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesiscited by 20
  20. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  21. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 19
  22. 2024Learning-based Multi-View Stereo: A Surveycited by 18
  23. 2024Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstructioncited by 18
  24. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 18
  25. 2024Novel View Synthesis with Pixel-Space Diffusion Modelscited by 16
  26. 2025LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Mergingcited by 16
  27. 2025MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Modelscited by 15
  28. 2024Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussianscited by 14
  29. 2024GSemSplat: Generalizable Semantic 3D Gaussian Splatting from Uncalibrated Image Pairscited by 14
  30. 2025Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Modelcited by 13
  31. 2025VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modelingcited by 12
  32. 2025ReSplat: Learning Recurrent Gaussian Splattingcited by 12
  33. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 11
  34. 2025Revisiting Depth Representations for Feed-Forward 3D Gaussian Splattingcited by 10
  35. 2025CL-Splats: Continual Learning of Gaussian Splatting with Local Optimizationcited by 10
  36. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 10
  37. 2024A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervisioncited by 9
  38. 2025I2V3D: Controllable image-to-video generation with 3D guidancecited by 9

50 most cited of 113 All 113 (JSON)