# Self-supervised Wide Baseline Visual Servoing via 3D Equivariance

arXiv: https://arxiv.org/abs/2209.05432 · HTML: https://mlsanity.com/paper/2209.05432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 12 Sep 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [Relative Camera Pose Estimation Using Convolutional Neural Networks](https://mlsanity.com/paper/1702.01381/) (2017)
- [Learning image representations tied to ego-motion](https://mlsanity.com/paper/1505.02206/) (2015)
- [Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms](https://mlsanity.com/paper/2105.14246/) (2021)
- [KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics Manipulation](https://mlsanity.com/paper/2007.13960/) (2020)
- [Self-Driving Car Steering Angle Prediction Based on Image Recognition](https://mlsanity.com/paper/1912.05440/) (2019)
- [Siamese Convolutional Neural Network for Sub-millimeter-accurate Camera Pose Estimation and Visual Servoing](https://mlsanity.com/paper/1903.04713/) (2019)
- [Learning Visual Servoing with Deep Features and Fitted Q-Iteration](https://mlsanity.com/paper/1703.11000/) (2017)
- [Visual Servoing from Deep Neural Networks](https://mlsanity.com/paper/1705.08940/) (2017)

## Built on by (most cited first, 1 of 1)

- [ViT-VS: On the Applicability of Pretrained Vision Transformer Features for Generalizable Visual Servoing](https://mlsanity.com/paper/2503.04545/) (2025)

## Abstract (arXiv)

One of the challenging input settings for visual servoing is when the initial and goal camera views are far apart. Such settings are difficult because the wide baseline can cause drastic changes in object appearance and cause occlusions. This paper presents a novel self-supervised visual servoing method for wide baseline images which does not require 3D ground truth supervision. Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes. We learn a coherent visual representation by leveraging a geometric property called 3D equivariance-the representation is transformed in a predictable way as a function of 3D transformation. To ensure that the feature-space is faithful to the underlying geodesic space, a geodesic preserving constraint is applied in conjunction with the equivariance. We design a Siamese network that can effectively enforce these two geometric properties without requiring 3D supervision. With the learned model, the relative transformation can be inferred simply by following the gradient in the learned space and used as feedback for closed-loop visual servoing. Our method is evaluated on objects from the YCB dataset, showing meaningful outperformance on a visual servoing task, or object alignment task with respect to state-of-the-art approaches that use 3D supervision. Ours yields more than 35% average distance error reduction and more than 90% success rate with 3cm error tolerance.