# Monitored Distillation for Positive Congruent Depth Completion

arXiv: https://arxiv.org/abs/2203.16034 · HTML: https://mlsanity.com/paper/2203.16034/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 64 of its 90 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 64)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [Self-Supervised Monocular Depth Hints](https://mlsanity.com/paper/1909.09051/) (2019)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1808.00150/) (2018)
- [CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion](https://mlsanity.com/paper/1911.05377/) (2019)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)

## Built on by (most cited first, 24 of 24)

- [WorDepth: Variational Language Prior for Monocular Depth Estimation](https://mlsanity.com/paper/2404.03635/) (2024)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2212.04096/) (2022)
- [RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions](https://mlsanity.com/paper/2410.02924/) (2024)
- [AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation](https://mlsanity.com/paper/2310.09739/) (2023)
- [SuperPrimitive: Scene Reconstruction at a Primitive Level](https://mlsanity.com/paper/2312.05889/) (2023)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens](https://mlsanity.com/paper/2508.04928/) (2025)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [All-day Depth Completion](https://mlsanity.com/paper/2405.17315/) (2024)
- [UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completion](https://mlsanity.com/paper/2410.18074/) (2024)
- [Radar-Guided Polynomial Fitting for Metric Depth Estimation](https://mlsanity.com/paper/2503.17182/) (2025)
- [ETA: Energy-based Test-time Adaptation for Depth Completion](https://mlsanity.com/paper/2508.05989/) (2025)
- [GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding](https://mlsanity.com/paper/2505.10671/) (2025)
- [Deep Cost Ray Fusion for Sparse Depth Video Completion](https://mlsanity.com/paper/2409.14935/) (2024)
- [StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completion](https://mlsanity.com/paper/2512.13147/) (2025)
- [Triangular Consistency as a Universal Constraint for Learning Optical Flow](https://mlsanity.com/paper/2606.19938/) (2026)
- [VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds](https://mlsanity.com/paper/2608.20740/) (2026)
- [Sparse Depth-Guided Attention for Accurate Depth Completion: A Stereo-Assisted Monitored Distillation Approach](https://mlsanity.com/paper/2303.15840/) (2023)
- [DEUX: Active Exploration for Learning Unsupervised Depth Perception](https://mlsanity.com/paper/2310.06164/) (2023)
- [Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency](https://mlsanity.com/paper/2312.15263/) (2023)
- [Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completion](https://mlsanity.com/paper/2402.13579/) (2024)
- [From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation](https://mlsanity.com/paper/2608.27860/) (2026)

## Abstract (arXiv)

We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge distillation approach that yields a positive congruent training process, wherein a student model avoids learning the error modes of the teachers. In the absence of ground truth for model selection and training, our method, termed Monitored Distillation, allows a student to exploit a blind ensemble of teachers by selectively learning from predictions that best minimize the reconstruction error for a given image. Monitored Distillation yields a distilled depth map and a confidence map, or ``monitor'', for how well a prediction from a particular teacher fits the observed image. The monitor adaptively weights the distilled depth where if all of the teachers exhibit high residuals, the standard unsupervised image reconstruction loss takes over as the supervisory signal. On indoor scenes (VOID), we outperform blind ensembling baselines by 17.53% and unsupervised methods by 24.25%; we boast a 79% model size reduction while maintaining comparable performance to the best supervised method. For outdoors (KITTI), we tie for 5th overall on the benchmark despite not using ground truth. Code available at: https://github.com/alexklwong/mondi-python.