mlsanityData to 7 Oct 2026

DepthSplat: Connecting Gaussian Splatting and Depth

arXiv 2410.13862 ↗First posted 17 Oct 2024cs.CVcited by 275

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Gaussian splatting and single-view depth estimation are typically studied in isolation. In this paper, we present DepthSplat to connect Gaussian splatting and depth estimation and study their interactions. More specifically, we first contribute a robust multi-view depth model by leveraging pre-trained monocular depth features, leading to high-quality feed-forward 3D Gaussian splatting reconstructions. We also show that Gaussian splatting can serve as an unsupervised pre-training objective for learning powerful depth models from large-scale multi-view posed datasets. We validate the synergy between Gaussian splatting and depth estimation through extensive ablation and cross-task transfer experiments. Our DepthSplat achieves state-of-the-art performance on ScanNet, RealEstate10K and DL3DV datasets in terms of both depth estimation and novel view synthesis, demonstrating the mutual benefits of connecting both tasks. In addition, DepthSplat enables feed-forward reconstruction from 12 input views (512x960 resolutions) in 0.6 seconds.

Key facts. Cited by 275 papers in the map (data through 7 Oct 2026). Builds on 68 of its 85 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

68 of 85 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  10. 2022A ConvNet for the 2020scited by 3,545
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
38 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  4. 2024Depth Anything V2cited by 1,385
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  8. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  9. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  10. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  11. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  12. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  13. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  14. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  15. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  16. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  17. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  18. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  19. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  20. 2020Virtual KITTI 2cited by 345
  21. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  22. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  23. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  24. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  25. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  26. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  27. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  28. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  29. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  30. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  31. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
  32. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  33. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  34. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  35. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  36. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  37. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  38. 2022Generalizable Patch-Based Neural Renderingcited by 121

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 97; 2026: 167.

275 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  2. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  3. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  4. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  5. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  6. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  7. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  8. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 60
  9. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  10. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  11. 2025VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Predictioncited by 41
  12. 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 40
38 more
  1. 2025YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splattingcited by 34
  2. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generationcited by 33
  3. 2025WonderTurbo: Generating Interactive 3D World in 0.72 Secondscited by 31
  4. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 31
  5. 2025StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generationcited by 26
  6. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  7. 2025Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Imagescited by 25
  8. 2024Splatter-360: Generalizable 360circ Gaussian Splatting for Wide-baseline Panoramic Imagescited by 23
  9. 2024PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splattingcited by 23
  10. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  11. 2024MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Viewscited by 21
  12. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 20
  13. 2025ReferSplat: Referring Segmentation in 3D Gaussian Splattingcited by 20
  14. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  15. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 19
  16. 2024Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstructioncited by 18
  17. 2025Relative Pose Estimation through Affine Corrections of Monocular Depth Priorscited by 18
  18. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 18
  19. 2024SLGaussian: Fast Language Gaussian Splatting in Sparse Viewscited by 17
  20. 2025SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observationscited by 16
  21. 2025MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Modelscited by 15
  22. 2025RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenescited by 15
  23. 2025DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusioncited by 14
  24. 2025SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Imagescited by 13
  25. 2026Faster-GS: Analyzing and Improving Gaussian Splatting Optimizationcited by 13
  26. 2026TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructioncited by 13
  27. 2025FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstructioncited by 12
  28. 2025RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registrationcited by 12
  29. 2025LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Imagescited by 12
  30. 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splattingcited by 12
  31. 2025ReSplat: Learning Recurrent Gaussian Splattingcited by 12
  32. 2025QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initializationcited by 11
  33. 2025Depth Anything at Any Conditioncited by 11
  34. 2026TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokenscited by 11
  35. 2024OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilitiescited by 10
  36. 2025Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Featurescited by 10
  37. 2025Revisiting Depth Representations for Feed-Forward 3D Gaussian Splattingcited by 10
  38. 2025CL-Splats: Continual Learning of Gaussian Splatting with Local Optimizationcited by 10

50 most cited of 275 All 275 (JSON)