mlsanityData to 14 Oct 2026

DepthLab: From Partial to Complete

arXiv 2412.18153 ↗First posted 24 Dec 2024cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Missing values remain a common challenge for depth data across its wide range of applications, stemming from various causes like incomplete data acquisition and perspective alteration. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our model features two notable strengths: (1) it demonstrates resilience to depth-deficient regions, providing reliable completion for both continuous areas and isolated points, and (2) it faithfully preserves scale consistency with the conditioned known depth when filling in missing values. Drawing on these advantages, our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion, exceeding current solutions in both numerical performance and visual quality. Our project page with source code is available at https://johanan528.github.io/depthlab_web/.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 73 of its 88 references that are in the map. First posted on arXiv 24 Dec 2024.

Builds on

73 of 88 references.

References · 73

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2023Consistency Modelscited by 1,822
  7. 2021Vision Transformers for Dense Predictioncited by 1,803
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  10. 2024Depth Anything V2cited by 1,422
  11. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  12. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
38 more
  1. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  2. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  3. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  4. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  5. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  6. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  7. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  8. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  9. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  10. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  11. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
  12. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  13. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  14. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  15. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  16. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
  17. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  18. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  19. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  20. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusioncited by 202
  21. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  22. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
  23. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 169
  24. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
  25. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
  26. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  27. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  28. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  29. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  30. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  31. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 140
  32. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  33. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 94
  34. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  35. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  36. 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 82
  37. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  38. 2024DepthFM: Fast Monocular Depth Estimation with Flow Matchingcited by 76

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 12.

27 papers.

Sort:

By area:

  1. 2025DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generationcited by 40
  2. 2025Depth Anything with Any Priorcited by 36
  3. 2025OmniNWM: Omniscient Driving Navigation World Modelscited by 33
  4. 2025WonderTurbo: Generating Interactive 3D World in 0.72 Secondscited by 32
  5. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 23
  6. 2025WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perceptioncited by 16
  7. 2025VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenescited by 13
  8. 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronizationcited by 12
  9. 2025Depth Anything at Any Conditioncited by 12
  10. 2025DuCos: Duality Constrained Depth Super-Resolution via Foundation Modelcited by 11
  11. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  12. 2025MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstructioncited by 8
15 more
  1. 20254D Driving Scene Generation With Stereo Forcingcited by 8
  2. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  3. 2025LuciBot: Automated Robot Policy Learning from Generated Videoscited by 4
  4. 2026Large Depth Completion Model from Sparse Observationscited by 4
  5. 2025DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Imagecited by 3
  6. 2026VecGlypher: Unified Vector Glyph Generation with Language Modelscited by 3
  7. 2026StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completioncited by 3
  8. 2026LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Drivingcited by 2
  9. 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenescited by 2
  10. 2025Perfecting Depth: Uncertainty-Aware Enhancement of Metric Depthcited by 1
  11. 2026SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Drivingcited by 1
  12. 2025LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Renderingcited by 0
  13. 2026PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistencycited by 0
  14. 2026Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensorscited by 0
  15. 2026Pumpire: Unified Benchmark for Metric Distance Estimationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior
  2. 2024Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
  3. 2024SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps
  4. 2023Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
  5. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
  6. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
  7. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency
  8. 2025DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion