mlsanityData to 7 Oct 2026

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

arXiv 2601.04090 ↗First posted 7 Jan 2026cs.CVcited by 24

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

Abstract (arXiv)

We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an adapter on its tokens, which are regularized to align with the appearance latents of pre-trained video diffusion models. By jointly generating these disentangled yet aligned latents, Gen3R produces both RGB videos and corresponding 3D geometry, including camera poses, depth maps, and global point clouds. Experiments demonstrate that our approach achieves state-of-the-art results in single- and multi-image conditioned 3D scene generation. Additionally, our method can enhance the robustness of reconstruction by leveraging generative priors, demonstrating the mutual benefit of tightly coupling reconstruction and generative models.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 78 of its 96 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

78 of 96 references.

Closest ancestors · 21

Same direction, newest first

  1. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easy18 Aug
  2. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling10 Jul
  3. 2025GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting14 Apr
  4. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Models18 Mar
  5. 2025Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors17 Mar
  6. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation28 Jan
  7. 2025Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation9 Jan
  8. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation30 Dec
  9. 2024World-consistent Video Diffusion with Explicit 3D Modeling2 Dec
  10. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis25 Nov
  11. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion7 Nov
  12. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text25 Jun
9 more
  1. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  2. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  3. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  4. 2023WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space22 Nov
  5. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  7. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion2 Dec
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  9. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 57

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  9. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  10. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  11. 2021Vision Transformers for Dense Predictioncited by 1,789
  12. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
38 more
  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2024Depth Anything V2cited by 1,385
  3. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  4. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  6. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  7. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  8. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  9. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  10. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  11. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  12. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  13. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  14. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  15. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  16. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  17. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  18. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  19. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  20. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  21. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  22. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  23. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  24. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  25. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  26. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  27. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  28. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  29. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  30. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  31. 2025Streaming 4D Visual Geometry Transformercited by 147
  32. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  33. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  34. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
  35. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  36. 2025Aether: Geometric-Aware Unified World Modelingcited by 94
  37. 2025FastVGGT: Training-Free Acceleration of Visual Geometry Transformercited by 93
  38. 2024GenXD: Generating Any 3D and 4D Scenescited by 49

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 24.

24 papers.

Sort:

By area:

  1. 2026VGGT-Omegacited by 20
  2. 2026VGGT-World: Transforming VGGT into an Autoregressive Geometry World Modelcited by 11
  3. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 11
  4. 2026VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modelingcited by 6
  5. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  6. 2026RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Spacecited by 3
  7. 2026Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimationcited by 3
  8. 2026AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customizationcited by 2
  9. 2026ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolationcited by 1
  10. 2026OneWorld: Taming Scene Generation with 3D Unified Representation Autoencodercited by 1
  11. 2026CityRAG: Stepping Into a City via Spatially-Grounded Video Generationcited by 1
  12. 2026Feed-Forward Gaussian Splatting from Sparse Aerial Viewscited by 1
12 more
  1. 2026Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Drivingcited by 1
  2. 2026JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Spacecited by 1
  3. 2026Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Modelscited by 1
  4. 2026GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Modelscited by 0
  5. 2026GenRec: Knowing Where to Reconstruct and Where to Generatecited by 0
  6. 2026USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxescited by 0
  7. 2026Revisiting Local Context for Long-Horizon Streaming 3D Reconstructioncited by 0
  8. 2026RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generationcited by 0
  9. 2026World in World: Explore the World with World Modelscited by 0
  10. 2026GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generationcited by 0
  11. 2026Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Themcited by 0
  12. 2026GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Spacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videos
  2. 2025GEN3D: Generating Domain-Free 3D Scenes from a Single Image
  3. 2024LT3SD: Latent Trees for 3D Scene Diffusion
  4. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
  5. 2026ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
  6. 2026GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior
  7. 2024V3D: Video Diffusion Models are Effective 3D Generators
  8. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories