mlsanityData to 14 Oct 2026

MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation

arXiv 2307.14460 ↗First posted 26 Jul 2023cs.CVcited by 174

Not on the map. Why?

Abstract (arXiv)

We release MiDaS v3.1 for monocular depth estimation, offering a variety of new models based on different encoder backbones. This release is motivated by the success of transformers in computer vision, with a large variety of pretrained vision transformers now available. We explore how using the most promising vision transformers as image encoders impacts depth estimation quality and runtime of the MiDaS architecture. Our investigation also includes recent convolutional approaches that achieve comparable quality to vision transformers in image classification tasks. While the previous release MiDaS v3.0 solely leverages the vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT. These models offer different performance-runtime tradeoffs. The best model improves the depth estimation quality by 28% while efficient models enable downstream tasks requiring high frame rates. We also describe the general process for integrating new backbones. A video summarizing the work can be found at https://youtu.be/UjaeNNFf9sE and the code is available at https://github.com/isl-org/MiDaS.

Key facts. Cited by 174 papers in the map (data through 14 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

43 of 58 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2022A ConvNet for the 2020scited by 3,579
  11. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  12. 2019Searching for MobileNetV3cited by 1,994
31 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,803
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  5. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  7. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  8. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  9. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  10. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  11. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  12. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  13. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  14. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  15. 2022DeiT III: Revenge of the ViTcited by 419
  16. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  17. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 303
  18. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  19. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
  20. 2016Single-Image Depth Perception in the Wildcited by 180
  21. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
  22. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  23. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 94
  24. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  25. 2022Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarioscited by 65
  26. 2023LDM3D: Latent Diffusion Model for 3Dcited by 53
  27. 2023Monocular Visual-Inertial Depth Estimationcited by 18
  28. 2023ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesiscited by 17
  29. 2022Depth Map Decomposition for Monocular Depth Estimationcited by 16
  30. 2021M4Depth: Monocular depth estimation for autonomous vehicles in unseen environmentscited by 9
  31. 2022Vision-Based Environmental Perception for Autonomous Drivingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 70; 2025: 58; 2026: 39.

174 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,422
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  3. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  4. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  5. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  6. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  7. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  8. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  9. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
  10. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
  11. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 161
  12. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 87
38 more
  1. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  2. 2024pix2gestalt: Amodal Segmentation by Synthesizing Wholescited by 70
  3. 2024DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videoscited by 63
  4. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 57
  5. 2024Reconstructive Visual Instruction Tuningcited by 55
  6. 2023SceneWiz3D: Towards Text-guided 3D Scene Compositioncited by 54
  7. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priorscited by 54
  8. 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
  9. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  10. 2024GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removalcited by 39
  11. 2024Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentationcited by 38
  12. 2024Monocular Occupancy Prediction for Scalable Indoor Scenescited by 31
  13. 2025Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigationcited by 30
  14. 2024LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Modelcited by 26
  15. 2024Depth Prompting for Sensor-Agnostic Depth Estimationcited by 26
  16. 2024A Construct-Optimize Approach to Sparse View Synthesis without Camera Posecited by 25
  17. 2024OmniControlNet: Dual-stage Integration for Conditional Image Generationcited by 24
  18. 2025Back on Track: Bundle Adjustment for Dynamic Scene Reconstructioncited by 24
  19. 2024PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentationcited by 22
  20. 2024VEON: Vocabulary-Enhanced Occupancy Predictioncited by 22
  21. 2024RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scalecited by 20
  22. 2023NViST: In the Wild New View Synthesis from a Single Image with Transformerscited by 19
  23. 2024SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generationcited by 19
  24. 2024ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projectioncited by 19
  25. 2024A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpaintingcited by 18
  26. 2025Relative Pose Estimation through Affine Corrections of Monocular Depth Priorscited by 18
  27. 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
  28. 2025GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstructioncited by 17
  29. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  30. 2025WorldGrow: Generating Infinite 3D Worldcited by 16
  31. 2025Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimatorcited by 15
  32. 2024Track Everything Everywhere Fast and Robustlycited by 14
  33. 2024Fast Encoder-Based 3D from Casual Videos via Point Track Processingcited by 14
  34. 2025SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generationcited by 14
  35. 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splattingcited by 14
  36. 2024Depth Anything in Medical Images: A Comparative Studycited by 13
  37. 2024Transferring Relative Monocular Depth to Surgical Vision with Temporal Consistencycited by 13
  38. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 13

50 most cited of 174 All 174 (JSON)