mlsanityData to 7 Oct 2026

OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations

arXiv 2406.11711 ↗First posted 17 Jun 2024cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. It has important applications in various downstream tasks. In this paper, we present OGNI-DC, a novel framework for depth completion. The key to our method is "Optimization-Guided Neural Iterations" (OGNI). It consists of a recurrent unit that refines a depth gradient field and a differentiable depth integrator that integrates the depth gradients into a depth map. OGNI-DC exhibits strong generalization, outperforming baselines by a large margin on unseen datasets and across various sparsity levels. Moreover, OGNI-DC has high accuracy, achieving state-of-the-art performance on the NYUv2 and the KITTI benchmarks. Code is available at https://github.com/princeton-vl/OGNI-DC.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 46 of its 57 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

46 of 57 references.

References · 46

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  4. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  5. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  8. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  9. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  10. 2017Sparsity Invariant CNNscited by 325
  11. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  12. 2022Deep Patch Visual Odometrycited by 186
34 more
  1. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  2. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  3. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  4. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  5. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  6. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  7. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  8. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  9. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  10. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  11. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  12. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  13. 2022Deep Equilibrium Optical Flow Estimationcited by 63
  14. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  15. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  16. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 48
  17. 2020FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completioncited by 45
  18. 2023NDDepth: Normal-Distance Assisted Monocular Depth Estimationcited by 45
  19. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  20. 2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
  21. 2020Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fieldscited by 40
  22. 2020GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimationcited by 36
  23. 20173D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detectioncited by 35
  24. 2020Deformable spatial propagation network for depth completioncited by 30
  25. 2022IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertaintycited by 30
  26. 2022Sparsity Agnostic Depth Completioncited by 27
  27. 2019FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Imagecited by 26
  28. 2022GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNscited by 23
  29. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  30. 2016Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observationcited by 14
  31. 2022A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereocited by 11
  32. 2022Unsupervised confidence for LiDAR depth maps and applicationscited by 10
  33. 2022Total Variation Optimization Layers for Computer Visioncited by 8
  34. 2023SparseDC: Depth Completion from sparse and non-uniform inputscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 9; 2026: 11.

23 papers.

Sort:

By area:

  1. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 47
  2. 2025Depth Anything with Any Priorcited by 32
  3. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 28
  4. 2025Distilling Monocular Foundation Model for Fine-grained Depth Completioncited by 14
  5. 2025LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Meshcited by 11
  6. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  7. 2025Self-Supervised Sparse Sensor Fusion for Long Range Perceptioncited by 8
  8. 2024SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Mapscited by 7
  9. 2025Event-Driven Dynamic Scene Depth Completioncited by 5
  10. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistencycited by 4
  11. 2026IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splattingcited by 4
  12. 2026Depth Completion as Parameter-Efficient Test-Time Adaptationcited by 3
11 more
  1. 2025Learning Inverse Laplacian Pyramid for Progressive Depth Completioncited by 2
  2. 2026Gaussian Belief Propagation Network for Depth Completioncited by 1
  3. 2026The Midas Touch for Metric Depthcited by 1
  4. 2026OmniPoint: Universal Monocular Metric Pointcloud from Any Cameracited by 1
  5. 2025ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integrationcited by 0
  6. 2025Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Imagecited by 0
  7. 2026EndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completioncited by 0
  8. 2026No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistencycited by 0
  9. 2026Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusioncited by 0
  10. 2026Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensorscited by 0
  11. 2026Boosting Metric Depth Completion via Training-Free Adaptive Response Geometrycited by 0