mlsanityData to 13 Oct 2026

FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis

arXiv 2503.13265 ↗First posted 17 Mar 2025cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Generating flexible-view 3D scenes, including 360deg rotation and zooming, from single images is challenging due to a lack of 3D data. To this end, we introduce FlexWorld, a novel framework consisting of two key components: (1) a strong video-to-video (V2V) diffusion model to generate high-quality novel view images from incomplete input rendered from a coarse scene, and (2) a progressive expansion process to construct a complete 3D scene. In particular, leveraging an advanced pre-trained video model and accurate depth-estimated training pairs, our V2V model can generate novel views under large camera pose variations. Building upon it, FlexWorld progressively generates new 3D content and integrates it into the global scene through geometry-aware scene fusion. Extensive experiments demonstrate the effectiveness of FlexWorld in generating high-quality novel view videos and flexible-view 3D scenes from single images, achieving superior visual quality under multiple popular metrics and datasets compared to existing state-of-the-art methods. Qualitatively, we highlight that FlexWorld can generate high-fidelity scenes with flexible views like 360deg rotations and zooming. Project page: https://ml-gsai.github.io/FlexWorld.

Key facts. Cited by 37 papers in the map (data through 13 Oct 2026). Builds on 62 of its 72 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

62 of 72 references.

References · 62

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,082
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,170
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,323
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,019
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,550
  11. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,218
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,921
38 more
  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,625
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,539
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,490
  4. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,422
  5. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,212
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 965
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 965
  8. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 843
  9. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 839
  10. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 753
  11. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 732
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 673
  13. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 651
  14. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 571
  15. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 557
  16. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 521
  17. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 473
  18. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 466
  19. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 451
  20. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 427
  21. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 424
  22. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 398
  23. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 395
  24. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  25. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 345
  26. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 325
  27. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  28. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 279
  29. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  30. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 229
  31. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  32. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 164
  33. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  34. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  35. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 152
  36. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 141
  37. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 140
  38. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 137

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 13; 2026: 24.

37 papers.

Sort:

By area:

  1. 2025Video World Models with Long-term Spatial Memorycited by 128
  2. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 95
  3. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 89
  4. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 41
  5. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 34
  6. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 27
  7. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenescited by 26
  8. 2025Positional Encoding Fieldcited by 20
  9. 2025Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview imagescited by 16
  10. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  11. 20254DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Modelscited by 10
  12. 2026World Reconstruction From Inconsistent Viewscited by 8
25 more
  1. 2026Latent Spatial Memory for Video World Modelscited by 8
  2. 2025GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splattingcited by 6
  3. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
  4. 2026ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Modelscited by 6
  5. 2026AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Groundingcited by 5
  6. 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
  7. 2026GeoStream: Toward Precise Camera Controlled Streaming Video Generationcited by 4
  8. 2025GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generationcited by 3
  9. 2026CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedbackcited by 3
  10. 2026Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Modelscited by 3
  11. 2025DreamAnywhere: Object-Centric Panoramic 3D Scene Generationcited by 2
  12. 2026WorldAgents: Can Foundation Image Models be Agents for 3D World Models?cited by 2
  13. 2026Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scalecited by 2
  14. 2025CustomX: Unified Character, Action, and Scene Customization in Video World Modelscited by 1
  15. 2026GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Secondscited by 1
  16. 2026Pose-Aware Diffusion for 3D Generationcited by 1
  17. 2026LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)cited by 1
  18. 2026GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusioncited by 1
  19. 2026GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environmentscited by 1
  20. 2026NeoMap: Training-free Novel-View Synthesis from Single Images and Videoscited by 1
  21. 2026Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generationcited by 0
  22. 2026UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Modelscited by 0
  23. 2026WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesiscited by 0
  24. 2026Reflection-aware Generative Novel View Synthesiscited by 0
  25. 2026World in World: Explore the World with World Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
  2. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
  3. 2025VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
  4. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
  5. 2025FlashWorld: High-quality 3D Scene Generation within Seconds
  6. 2024V3D: Video Diffusion Models are Effective 3D Generators
  7. 2026Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction
  8. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints