# CopyQuad: Quadrupedal Skill Transfer from a Single Side-View Video Without a Depth Model

arXiv: https://arxiv.org/abs/2610.16737 · HTML: https://mlsanity.com/paper/2610.16737/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Visual Imitation Enables Contextual Humanoid Control](https://mlsanity.com/paper/2505.03729/) (2025)
- [Reconstructing Animatable Categories from Videos](https://mlsanity.com/paper/2305.06351/) (2023)
- [SuperAnimal pretrained pose estimation models for behavioral analysis](https://mlsanity.com/paper/2203.07436/) (2022)
- [Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models](https://mlsanity.com/paper/2308.15143/) (2023)
- [AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild](https://mlsanity.com/paper/2103.13282/) (2021)
- [SLoMo: A General System for Legged Robot Motion Imitation from Casual Videos](https://mlsanity.com/paper/2304.14389/) (2023)
- [Spatio-Temporal Motion Retargeting for Quadruped Robots](https://mlsanity.com/paper/2404.11557/) (2024)
- [Imitation and Adaptation Based on Consistency: A Quadruped Robot Imitates Animals from Videos Using Deep Reinforcement Learning](https://mlsanity.com/paper/2203.05973/) (2022)
- [Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation](https://mlsanity.com/paper/2507.06111/) (2025)
- [VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion](https://mlsanity.com/paper/2510.23997/) (2025)
- [Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives](https://mlsanity.com/paper/2410.10438/) (2024)
- [Reinforcement Learning from Wild Animal Videos](https://mlsanity.com/paper/2412.04273/) (2024)

## Abstract (arXiv)

Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to recover the one axis a side-view camera cannot see. We present CopyQuad, which omits that stage and pins the missing axis to the robot's own stance width instead. The setting is side-view footage of sagittally dominated motion, where limb motion is almost entirely in the image plane. A frozen 2D keypoint detector and a fixed analytic retargeting then turn a single uncalibrated clip into a robot reference whose foot targets are reachable by construction, so no per-clip trajectory optimization is needed. One phase-indexed reward structure, whose only per-behavior freedom is three scalars from a shared sweep, learns a dog walk, a horse walk, a horse trot and two non-periodic gestures, all deployed zero-shot on hardware. We then measure what omitting the axis costs. In a training-free rigidity test, a video depth model varies the distance between the animal's hips by 40 to 107% of its own mean and a single-image metric model by 22 to 58%, though that distance cannot move. Motion capture puts the true lateral paw travel of a dog walk at 4.5 cm peak to peak, a mean deviation near 1.4 cm against the 3.5 cm of lateral foot error our policies already leave, so the discarded axis sits below the pipeline's resolution. Depth repaired to feasibility never beats the constant, and the unrepaired estimates put the robot on the ground.