mlsanityData to 14 Oct 2026

OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration

arXiv 2411.19278 ↗First posted 28 Nov 2024cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose OMNI-DC, a highly robust DC model that generalizes well zero-shot to various datasets. The key design is a novel Multi-resolution Depth Integrator, allowing our model to deal with very sparse depth inputs. We also introduce a novel Laplacian loss to model the ambiguity in the training process. Moreover, we train OMNI-DC on a mixture of high-quality datasets with a scale normalization technique and synthetic depth patterns. Extensive experiments on 7 datasets show consistent improvements over baselines, reducing errors by as much as 43%. Codes and checkpoints are available at https://github.com/princeton-vl/OMNI-DC.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 60 of its 77 references that are in the map. First posted on arXiv 28 Nov 2024.

Builds on

60 of 77 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2016Layer Normalizationcited by 5,669
  9. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  11. 2024Depth Anything V2cited by 1,422
  12. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
38 more
  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  2. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  3. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  4. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  5. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  6. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  7. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  8. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  9. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  10. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  11. 2017Sparsity Invariant CNNscited by 326
  12. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  13. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  14. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
  15. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
  16. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  17. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 173
  18. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 138
  19. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  20. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
  21. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  22. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  23. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  24. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 93
  25. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 89
  26. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  27. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  28. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 71
  29. 2024Bilateral Propagation Network for Depth Completioncited by 60
  30. 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereocited by 50
  31. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 49
  32. 2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
  33. 20173D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detectioncited by 35
  34. 2021Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Networkcited by 33
  35. 2020Deformable spatial propagation network for depth completioncited by 30
  36. 2022Sparsity Agnostic Depth Completioncited by 27
  37. 2023On the Importance of Accurate Geometry Data for Dense 3D Vision Taskscited by 26
  38. 2024Test-Time Adaptation for Depth Completioncited by 26

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 24.

30 papers.

Sort:

By area:

  1. 2025Depth Anything with Any Priorcited by 36
  2. 2026Masked Depth Modeling for Spatial Perceptioncited by 28
  3. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 23
  4. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  5. 2026Any to Full: Prompting Depth Anything for Depth Completion in One Stagecited by 5
  6. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistencycited by 4
  7. 2026Large Depth Completion Model from Sparse Observationscited by 4
  8. 2025DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Imagecited by 3
  9. 2026Depth Completion as Parameter-Efficient Test-Time Adaptationcited by 3
  10. 2026StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completioncited by 3
  11. 2026GGPT: Geometry Grounded Point Transformercited by 3
  12. 2026LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Drivingcited by 2
18 more
  1. 2026AURORA-KITTI: Any-Weather Depth Completion and Denoisingcited by 2
  2. 2025DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidancecited by 1
  3. 2026SpiderCam: Low-Power Snapshot Depth from Differential Defocuscited by 1
  4. 2026SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Drivingcited by 1
  5. 2026VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Cloudscited by 1
  6. 2025RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulationcited by 0
  7. 2025Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoderscited by 0
  8. 2026Robust Depth Super-Resolution via Adaptive Diffusion Samplingcited by 0
  9. 2026No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistencycited by 0
  10. 2026Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusioncited by 0
  11. 2026ToFormer: Towards Large-scale Scenario Depth Completion for Lightweight ToF Cameracited by 0
  12. 2026Zero-Shot Depth from Defocuscited by 0
  13. 2026UniT: Unified Geometry Learning with Group Autoregressive Transformercited by 0
  14. 2026Streaming Neural Speech Codecs through Time-Invariant Representationscited by 0
  15. 2026Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensorscited by 0
  16. 2026Boosting Metric Depth Completion via Training-Free Adaptive Response Geometrycited by 0
  17. 2026The Midas Touch for Metric Depth: Interpretable Metricization for Generalizable Depth Perceptioncited by 0
  18. 2026Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completioncited by 0