mlsanityData to 14 Oct 2026

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

arXiv 2505.23716 ↗First posted 29 May 2025cs.CVcited by 243

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce AnySplat, a feed forward network for novel view synthesis from uncalibrated image collections. In contrast to traditional neural rendering pipelines that demand known camera poses and per scene optimization, or recent feed forward methods that buckle under the computational weight of dense views, our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi view datasets without any pose annotations. In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios while surpassing existing pose free approaches. Moreover, it greatly reduce rendering latency compared to optimization based neural fields, bringing real time novel view synthesis within reach for unconstrained capture settings.Project page: https://city-super.github.io/anysplat/

Key facts. Cited by 243 papers in the map (data through 14 Oct 2026). Builds on 63 of its 79 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

63 of 79 references.

References · 63

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  8. 2021Vision Transformers for Dense Predictioncited by 1,803
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  12. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
38 more
  1. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  4. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  5. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  6. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  7. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  8. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  9. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  11. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  12. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  13. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  14. 2023LERF: Language Embedded Radiance Fieldscited by 543
  15. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  16. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  17. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  18. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  19. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  20. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  21. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  22. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  23. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  24. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  25. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  26. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  27. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 230
  28. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  29. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  30. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  31. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  32. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  33. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  34. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  35. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  36. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  37. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  38. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 44; 2026: 199.

243 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  2. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  3. 2025VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Predictioncited by 48
  4. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  5. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  6. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  7. 2025FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Predictioncited by 38
  8. 2025YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splattingcited by 37
  9. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 37
  10. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 32
  11. 2026Gen3R: 3D Scene Generation Meets Feed-Forward Reconstructioncited by 31
  12. 2025IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstructioncited by 28
38 more
  1. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  2. 2025Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Imagescited by 26
  3. 2025SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Modelscited by 26
  4. 2026ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Trainingcited by 26
  5. 2026VGGT-Omegacited by 26
  6. 2025ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splattingcited by 25
  7. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 22
  8. 2025C3G: Learning Compact 3D Representations with 2K Gaussianscited by 21
  9. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  10. 2026Faster-GS: Analyzing and Improving Gaussian Splatting Optimizationcited by 17
  11. 2025ReSplat: Learning Recurrent Gaussian Splattingcited by 15
  12. 2026TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructioncited by 14
  13. 2026GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokenscited by 12
  14. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  15. 2025Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splattingcited by 11
  16. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 11
  17. 2025EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Imagescited by 10
  18. 2025ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representationcited by 9
  19. 2026LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesiscited by 9
  20. 2025VGGT-X: When VGGT Meets Dense Novel View Synthesiscited by 8
  21. 2026Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesiscited by 8
  22. 2026AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priorscited by 8
  23. 2026Vision Pretraining for Dense Spatial Perceptioncited by 8
  24. 2025E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Modelscited by 7
  25. 2025FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformerscited by 7
  26. 2025SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 7
  27. 2025Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videoscited by 7
  28. 2026GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generatorcited by 7
  29. 2026SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Predictioncited by 7
  30. 2026One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusioncited by 6
  31. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 6
  32. 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fieldscited by 6
  33. 2026ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstructioncited by 6
  34. 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligencecited by 6
  35. 2026Omni-3DEdit: Generalized Versatile 3D Editing in One-Passcited by 6
  36. 2026OccAny: Generalized Unconstrained Urban 3D Occupancycited by 6
  37. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  38. 2026From Rays to Projections: Better Inputs for Feed-Forward View Synthesiscited by 5

50 most cited of 243 All 243 (JSON)