mlsanityData to 7 Oct 2026

Sharp Monocular View Synthesis in Less Than a Second

arXiv 2512.10685 ↗First posted 11 Dec 2025cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Experimental results demonstrate that SHARP delivers robust zero-shot generalization across datasets. It sets a new state of the art on multiple datasets, reducing LPIPS by 25-34% and DISTS by 21-43% versus the best prior model, while lowering the synthesis time by three orders of magnitude. Code and weights are provided at https://github.com/apple/ml-sharp

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 58 of its 72 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

58 of 72 references.

References · 58

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  7. 2021Vision Transformers for Dense Predictioncited by 1,789
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  11. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  12. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
38 more
  1. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  2. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  4. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  5. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  6. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  8. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  9. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  10. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  11. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  12. 2021Advances in Neural Renderingcited by 365
  13. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  14. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  15. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  16. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  17. 2022Novel View Synthesis with Diffusion Modelscited by 299
  18. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  19. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  20. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  21. 2020Free View Synthesiscited by 231
  22. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  23. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  24. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  25. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  26. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  27. 2016View Synthesis by Appearance Flowcited by 172
  28. 2020Stable View Synthesiscited by 165
  29. 2022FILM: Frame Interpolation for Large Motioncited by 149
  30. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  31. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
  32. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  33. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Imagecited by 109
  34. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  35. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  36. 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
  37. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  38. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 19.

19 papers.

Sort:

By area:

  1. 2026World Reconstruction From Inconsistent Viewscited by 8
  2. 2026MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffoldcited by 3
  3. 2026NanoGS: Training-Free Gaussian Splat Simplificationcited by 2
  4. 2026UniSHARP: Universal Sharp Monocular View Synthesiscited by 2
  5. 2026HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Videocited by 1
  6. 2026Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulationcited by 1
  7. 2026QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Predictioncited by 1
  8. 2026The Role of Initialization in 3D Gaussian Splattingcited by 0
  9. 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generationcited by 0
  10. 2026Zero-Shot Depth from Defocuscited by 0
  11. 2026Clustered Codebook Quantization for 2D Gaussian-based Image Compressioncited by 0
  12. 2026LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splattingcited by 0
7 more
  1. 2026CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstructioncited by 0
  2. 2026PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructionscited by 0
  3. 2026Spackle: Completing Large View Single Image NVS with Adaptive Gaussianscited by 0
  4. 2026VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesiscited by 0
  5. 2026GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Spacecited by 0
  6. 2026StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Imagescited by 0
  7. 2026GenIA: Generative Reconstruction with Test-Time Input Alignmentcited by 0