mlsanityData to 14 Oct 2026

Bolt3D: Generating 3D Scenes in Seconds

arXiv 2503.14445 ↗First posted 18 Mar 2025cs.CVcited by 59

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

Abstract (arXiv)

We present a latent diffusion model for fast feed-forward 3D scene generation. Given one or more images, our model Bolt3D directly samples a 3D scene representation in less than seven seconds on a single GPU. We achieve this by leveraging powerful and scalable existing 2D diffusion network architectures to produce consistent high-fidelity 3D scene representations. To train this model, we create a large-scale multiview-consistent dataset of 3D geometry and appearance by applying state-of-the-art dense 3D reconstruction techniques to existing multiview image datasets. Compared to prior multiview generative models that require per-scene optimization for 3D reconstruction, Bolt3D reduces the inference cost by a factor of up to 300 times.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 96 of its 114 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

96 of 114 references.

Closest ancestors · 32

Same direction, newest first

  1. 2025Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors17 Mar
  2. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation28 Jan
  3. 2025Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation9 Jan
  4. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation30 Dec
  5. 2024Wonderland: Navigating 3D Scenes from a Single Image16 Dec
  6. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale9 Dec
  7. 2024World-consistent Video Diffusion with Explicit 3D Modeling2 Dec
  8. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models27 Nov
  9. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion7 Nov
  10. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplats26 Oct
  11. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis3 Sep
  12. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model29 Aug
20 more
  1. 2024MultiDiff: Consistent Novel View Synthesis from a Single Image26 Jun
  2. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  3. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  4. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion10 Apr
  5. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  6. 2024Denoising Diffusion via Image-Based Rendering5 Feb
  7. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  8. 2023WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space22 Nov
  9. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  10. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image27 Oct
  11. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  12. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data13 Jun
  13. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models21 Apr
  14. 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models19 Apr
  15. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr
  16. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  17. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  18. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion2 Dec
  19. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation17 Nov
  20. 2022Novel View Synthesis with Diffusion Models6 Oct

Other references · 64

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  9. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  11. 2021Vision Transformers for Dense Predictioncited by 1,803
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
38 more
  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  4. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  7. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  8. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  9. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  13. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  14. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  15. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  16. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  17. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  18. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  19. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  20. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  21. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  22. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  23. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  24. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  25. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  26. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  27. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  28. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  29. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  30. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  31. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  32. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 180
  33. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  34. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  35. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  36. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  37. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  38. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 23; 2026: 36.

59 papers.

Sort:

By area:

  1. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 67
  2. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  3. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  4. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 32
  5. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  6. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenescited by 26
  7. 20253D Scene Generation: A Surveycited by 24
  8. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 20
  9. 2025WorldGen: From Text to Traversable and Interactive 3D Worldscited by 19
  10. 2025GeoVideo: Introducing Geometric Regularization into Video Generation Modelcited by 19
  11. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 18
  12. 2025MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatarscited by 17
38 more
  1. 2025SPATIALGEN: Layout-guided 3D Indoor Scene Generationcited by 14
  2. 2026RayRoPE: Projective Ray Positional Encoding for Multi-view Attentioncited by 14
  3. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 14
  4. 2025See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpaintingcited by 12
  5. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  6. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 11
  7. 2025CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Modelscited by 10
  8. 2026SceneTok: A Compressed, Diffusable Token Space for 3D Scenescited by 10
  9. 2026LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesiscited by 9
  10. 2025One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Controlcited by 8
  11. 2026World Reconstruction From Inconsistent Viewscited by 8
  12. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Modelscited by 7
  13. 2026NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstructioncited by 7
  14. 2026GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generatorcited by 7
  15. 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimationcited by 7
  16. 2025GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splattingcited by 6
  17. 2025Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussianscited by 6
  18. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  19. 2026RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Spacecited by 5
  20. 2025View-Consistent Diffusion Representations for 3D-Consistent Video Generationcited by 4
  21. 2026GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Viewscited by 4
  22. 2026Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priorscited by 4
  23. 2026Syn4D: A Multiview Synthetic 4D Datasetcited by 4
  24. 2026MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAEcited by 3
  25. 2025Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planningcited by 2
  26. 2025Complete Gaussian Splats from a Single Image with Denoising Diffusion Modelscited by 2
  27. 2026Dark3R: Learning Structure from Motion in the Darkcited by 2
  28. 2026Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstructioncited by 2
  29. 2025CustomX: Unified Character, Action, and Scene Customization in Video World Modelscited by 1
  30. 2026PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modelingcited by 1
  31. 2026InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesiscited by 1
  32. 2026Sparse auto-regressive modeling for scene generation from multi-view imagescited by 1
  33. 2025Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Imagescited by 0
  34. 2026ATATA: One Algorithm to Align Them Allcited by 0
  35. 2026Projected Representation Conditioning for High-fidelity Novel View Synthesiscited by 0
  36. 2026SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesiscited by 0
  37. 2026Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generationcited by 0
  38. 20263DTV: A Feedforward Interpolation Network for Real-Time View Synthesiscited by 0

50 most cited of 59 All 59 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
  2. 2024LT3SD: Latent Trees for 3D Scene Diffusion
  3. 2026Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
  4. 2026Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
  5. 2024V3D: Video Diffusion Models are Effective 3D Generators
  6. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  7. 2024Hash3D: Training-free Acceleration for 3D Generation
  8. 2025Recent Advances in 3D Object and Scene Generation: A Survey