# KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo

arXiv: https://arxiv.org/abs/2207.10425 · HTML: https://mlsanity.com/paper/2207.10425/

## Key facts

- Cited by 18 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 36 of its 47 references that are in the map.
- First posted on arXiv 21 Jul 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 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [Cost Volume Pyramid Based Depth Inference for Multi-View Stereo](https://mlsanity.com/paper/1912.08329/) (2019)
- [Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness](https://mlsanity.com/paper/1911.12012/) (2019)
- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)
- [Multi-Scale Geometric Consistency Guided Multi-View Stereo](https://mlsanity.com/paper/1904.08103/) (2019)
- [Visibility-aware Multi-view Stereo Network](https://mlsanity.com/paper/2008.07928/) (2020)
- [Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking](https://mlsanity.com/paper/2007.10872/) (2020)
- [AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network](https://mlsanity.com/paper/2108.03824/) (2021)
- [Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency](https://mlsanity.com/paper/1905.02706/) (2019)
- [Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation](https://mlsanity.com/paper/2104.05374/) (2021)
- [Digging into Uncertainty in Self-supervised Multi-view Stereo](https://mlsanity.com/paper/2108.12966/) (2021)

## Built on by (most cited first, 18 of 18)

- [MVImgNet: A Large-scale Dataset of Multi-view Images](https://mlsanity.com/paper/2303.06042/) (2023)
- [MoCha-Stereo: Motif Channel Attention Network for Stereo Matching](https://mlsanity.com/paper/2404.06842/) (2024)
- [C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction](https://mlsanity.com/paper/2306.10003/) (2023)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth](https://mlsanity.com/paper/2406.00474/) (2024)
- [Geometry Field Splatting with Gaussian Surfels](https://mlsanity.com/paper/2411.17067/) (2024)
- [GRAPE: Generalizable and Robust Multi-view Facial Capture](https://mlsanity.com/paper/2407.10193/) (2024)
- [Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware](https://mlsanity.com/paper/2602.00865/) (2026)
- [RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions](https://mlsanity.com/paper/2509.19165/) (2025)
- [SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation](https://mlsanity.com/paper/2604.10218/) (2026)
- [ES-MVSNet: Efficient Framework for End-to-end Self-supervised Multi-View Stereo](https://mlsanity.com/paper/2308.02191/) (2023)
- [EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency](https://mlsanity.com/paper/2408.05452/) (2024)
- [Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation](https://mlsanity.com/paper/2304.12685/) (2023)
- [Prism: Semi-Supervised Multi-View Stereo with Monocular Structure Priors](https://mlsanity.com/paper/2412.05771/) (2024)
- [Boosting Multi-View Stereo with Depth Foundation Model in the Absence of Real-World Labels](https://mlsanity.com/paper/2504.11845/) (2025)
- [MAGIC: Learning from Visibility Asymmetry for Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.10838/) (2025)
- [BINO: Encoder Centric Self Supervised Stereo With Native Pair Input](https://mlsanity.com/paper/2603.27904/) (2026)
- [OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute](https://mlsanity.com/paper/2609.36374/) (2026)

## Abstract (arXiv)

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth. In this paper, we propose a novel self-supervised training pipeline for MVS based on knowledge distillation, termed KD-MVS, which mainly consists of self-supervised teacher training and distillation-based student training. Specifically, the teacher model is trained in a self-supervised fashion using both photometric and featuremetric consistency. Then we distill the knowledge of the teacher model to the student model through probabilistic knowledge transferring. With the supervision of validated knowledge, the student model is able to outperform its teacher by a large margin. Extensive experiments performed on multiple datasets show our method can even outperform supervised methods.