mlsanityData to 14 Oct 2026

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

arXiv 2405.17251 ↗First posted 27 May 2024cs.CVcited by 73

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image (T2I) models with monocular depth estimation (MDE) has shown promise in handling in-the-wild images. In these methods, an input view is geometrically warped to novel views with estimated depth maps, then the warped image is inpainted by T2I models. However, they struggle with noisy depth maps and loss of semantic details when warping an input view to novel viewpoints. In this paper, we propose a novel approach for single-shot novel view synthesis, a semantic-preserving generative warping framework that enables T2I generative models to learn where to warp and where to generate, through augmenting cross-view attention with self-attention. Our approach addresses the limitations of existing methods by conditioning the generative model on source view images and incorporating geometric warping signals. Qualitative and quantitative evaluations demonstrate that our model outperforms existing methods in both in-domain and out-of-domain scenarios. Project page is available at https://GenWarp-NVS.github.io/.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

45 of 54 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  11. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  12. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
33 more
  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  6. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  7. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  8. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  9. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  10. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 670
  11. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  12. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  13. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  14. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  15. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  16. 2022Novel View Synthesis with Diffusion Modelscited by 300
  17. 2020Softmax Splatting for Video Frame Interpolationcited by 279
  18. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
  19. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  20. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  21. 2023Style Aligned Image Generation via Shared Attentioncited by 216
  22. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  23. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  24. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
  25. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 100
  26. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  27. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  28. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  29. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Modelscited by 76
  30. 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
  31. 2023Text2Immersion: Generative Immersive Scene with 3D Gaussianscited by 43
  32. 2022Simple and Effective Synthesis of Indoor 3D Scenescited by 33
  33. 2022CoordGAN: Self-Supervised Dense Correspondences Emerge from GANscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 33; 2026: 31.

73 papers.

Sort:

By area:

  1. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  2. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 178
  3. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 109
  4. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 101
  5. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 95
  6. 2025World-in-World: World Models in a Closed-Loop Worldcited by 47
  7. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  8. 2024VistaDream: Sampling multiview consistent images for single-view scene reconstructioncited by 38
  9. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Modelcited by 32
  10. 2025SynCity: Training-Free Generation of 3D Worldscited by 31
  11. 2024DepthLab: From Partial to Completecited by 27
  12. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
38 more
  1. 2025EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidancecited by 21
  2. 2025Pippo: High-Resolution Multi-View Humans from a Single Imagecited by 20
  3. 2025Positional Encoding Fieldcited by 20
  4. 2024ObjCtrl-2.5D: Training-free Object Control with Camera Posescited by 18
  5. 2024Novel View Synthesis with Pixel-Space Diffusion Modelscited by 16
  6. 2025SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observationscited by 16
  7. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 15
  8. 2026Repurposing Geometric Foundation Models for Multi-view Diffusioncited by 15
  9. 2026ReRoPE: Repurposing RoPE for Relative Camera Controlcited by 13
  10. 2025See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpaintingcited by 12
  11. 2026Grounding World Simulation Models in a Real-World Metropoliscited by 12
  12. 2025High-Fidelity Novel View Synthesis via Splatting-Guided Diffusioncited by 11
  13. 2025Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpaintingcited by 11
  14. 2025ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encodingcited by 11
  15. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 11
  16. 2025InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problemscited by 10
  17. 2025OmniCam: Unified Multimodal Video Generation via Camera Controlcited by 9
  18. 2024KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photoscited by 7
  19. 2025Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometrycited by 7
  20. 2025Towards Open-World Generation of Stereo Images and Unsupervised Matchingcited by 6
  21. 2025WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusioncited by 6
  22. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 6
  23. 2025Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillationcited by 5
  24. 2025CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenizationcited by 5
  25. 2026AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Groundingcited by 5
  26. 2024ControlFace: Harnessing Facial Parametric Control for Face Riggingcited by 4
  27. 2025Pointmap-Conditioned Diffusion for Consistent Novel View Synthesiscited by 4
  28. 2024Towards a Science Exocortexcited by 3
  29. 2025WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Imagecited by 3
  30. 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusioncited by 3
  31. 2025Fillerbuster: Unified Generative Scene Completion Model for Casual Capturescited by 2
  32. 2025Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completioncited by 2
  33. 2025Sketch3DVE: Sketch-based 3D-Aware Scene Video Editingcited by 2
  34. 2025StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Spacecited by 2
  35. 2026Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Viewscited by 2
  36. 2026TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Imagecited by 2
  37. 2025SparsyFed: Sparse Adaptive Federated Trainingcited by 1
  38. 2026DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesiscited by 1

50 most cited of 73 All 73 (JSON)