# ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation

arXiv: https://arxiv.org/abs/2112.02772 · HTML: https://mlsanity.com/paper/2112.02772/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (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)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Intel RealSense Stereoscopic Depth Cameras](https://mlsanity.com/paper/1705.05548/) (2017)
- [Computing the Stereo Matching Cost with a Convolutional Neural Network](https://mlsanity.com/paper/1409.4326/) (2014)
- [ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems](https://mlsanity.com/paper/1807.06009/) (2018)
- [Self-Supervised Learning for Stereo Matching with Self-Improving Ability](https://mlsanity.com/paper/1709.00930/) (2017)
- [StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching](https://mlsanity.com/paper/2005.01927/) (2020)
- [Applying Depth-Sensing to Automated Surgical Manipulation with a da Vinci Robot](https://mlsanity.com/paper/2002.06302/) (2020)

## Built on by (most cited first, 7 of 7)

- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera](https://mlsanity.com/paper/2405.05648/) (2024)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2509.06233/) (2025)
- [TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touches](https://mlsanity.com/paper/2309.09427/) (2023)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)
- [ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection](https://mlsanity.com/paper/2408.06592/) (2024)

## Abstract (arXiv)

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.