mlsanityData to 7 Oct 2026

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

arXiv 2503.03751 ↗First posted 5 Mar 2025cs.CV cs.GRcited by 325

Not on the map. Why?

Cited by 102 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage little 3D information, leading to inconsistencies, such as objects popping in and out of existence. Camera control, if implemented at all, is imprecise, because camera parameters are mere inputs to the neural network which must then infer how the video depends on the camera. In contrast, GEN3C is guided by a 3D cache: point clouds obtained by predicting the pixel-wise depth of seed images or previously generated frames. When generating the next frames, GEN3C is conditioned on the 2D renderings of the 3D cache with the new camera trajectory provided by the user. Crucially, this means that GEN3C neither has to remember what it previously generated nor does it have to infer the image structure from the camera pose. The model, instead, can focus all its generative power on previously unobserved regions, as well as advancing the scene state to the next frame. Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis, even in challenging settings such as driving scenes and monocular dynamic video. Results are best viewed in videos. Check out our webpage! https://research.nvidia.com/labs/toronto-ai/GEN3C/

Key facts. Cited by 325 papers in the map (data through 7 Oct 2026). Builds on 66 of its 79 references that are in the map. First posted on arXiv 5 Mar 2025.

Builds on

66 of 79 references.

References · 66

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  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. 2022Generative Adversarial Networkscited by 5,603
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  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. 2017Decoupled Weight Decay Regularizationcited by 1,722
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
38 more
  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  4. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  5. 2024Depth Anything V2cited by 1,385
  6. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  8. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  9. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  10. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  11. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  12. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  13. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  14. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  15. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  16. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  17. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  18. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  19. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  20. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  21. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  22. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  23. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  24. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  25. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  26. 2022Kubric: A scalable dataset generatorcited by 373
  27. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  28. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  29. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  30. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  31. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  32. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  33. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 242
  34. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  35. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  36. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  37. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 185
  38. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 120; 2026: 205.

325 papers.

Sort:

By area:

  1. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  2. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  3. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
  4. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  5. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 157
  6. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 152
  7. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  8. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 126
  9. 2025Video World Models with Long-term Spatial Memorycited by 124
  10. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  11. 2025Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Controlcited by 95
  12. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 93
38 more
  1. 2025Controllable Video Generation: A Surveycited by 93
  2. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 89
  3. 2025Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Modelscited by 80
  4. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 75
  5. 2025Follow-Your-Creation: Empowering 4D Creation through Video Inpaintingcited by 61
  6. 2025CamCloneMaster: Enabling Reference-based Camera Control for Video Generationcited by 44
  7. 2025World-in-World: World Models in a Closed-Loop Worldcited by 44
  8. 2025DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generationcited by 39
  9. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 39
  10. 2025VRAG: Learning World Models for Interactive Video Generationcited by 37
  11. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 37
  12. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 36
  13. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  14. 2025Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Controlcited by 33
  15. 2025Matrix-3D: Omnidirectional Explorable 3D World Generationcited by 33
  16. 2025FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Predictioncited by 33
  17. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 33
  18. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easycited by 31
  19. 2026Rethinking Video Generation Model for the Embodied Worldcited by 30
  20. 2025ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulationcited by 28
  21. 2025Dynamic Camera Poses and Where to Find Themcited by 26
  22. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenescited by 26
  23. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 26
  24. 2026Gen3R: 3D Scene Generation Meets Feed-Forward Reconstructioncited by 24
  25. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  26. 2026MosaicMem: Hybrid Spatial Memory for Controllable Video World Modelscited by 23
  27. 2025PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanismscited by 22
  28. 2025Generative Video Motion Editing with 3D Point Trackscited by 21
  29. 2025EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidancecited by 20
  30. 2025PlayerOne: Egocentric World Simulatorcited by 20
  31. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  32. 2025Positional Encoding Fieldcited by 20
  33. 2025Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generationcited by 19
  34. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 19
  35. 2026VGGRPO: Towards World-Consistent Video Generation with 4D Latent Rewardcited by 19
  36. 2025WorldGen: From Text to Traversable and Interactive 3D Worldscited by 18
  37. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 18
  38. 2025StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splattingcited by 17

50 most cited of 325 All 325 (JSON)