# Diffusing in Someone Else's Shoes: Robotic Perspective Taking with Diffusion

arXiv: https://arxiv.org/abs/2404.07735 · HTML: https://mlsanity.com/paper/2404.07735/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot](https://mlsanity.com/paper/2307.00595/) (2023)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations](https://mlsanity.com/paper/1912.04344/) (2019)
- [Third-Person Imitation Learning](https://mlsanity.com/paper/1703.01703/) (2017)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [NICOL: A Neuro-inspired Collaborative Semi-humanoid Robot that Bridges Social Interaction and Reliable Manipulation](https://mlsanity.com/paper/2305.08528/) (2023)
- [CycleIK: Neuro-inspired Inverse Kinematics](https://mlsanity.com/paper/2307.11554/) (2023)

## Built on by (most cited first, 4 of 4)

- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [Egocentric and Exocentric Methods: A Short Survey](https://mlsanity.com/paper/2410.20621/) (2024)
- [DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion Model](https://mlsanity.com/paper/2501.16800/) (2025)
- [Keypoint-based Diffusion for Robotic Motion Planning on the NICOL Robot](https://mlsanity.com/paper/2509.04076/) (2025)

## Abstract (arXiv)

Humanoid robots can benefit from their similarity to the human shape by learning from humans. When humans teach other humans how to perform actions, they often demonstrate the actions, and the learning human imitates the demonstration to get an idea of how to perform the action. Being able to mentally transfer from a demonstration seen from a third-person perspective to how it should look from a first-person perspective is fundamental for this ability in humans. As this is a challenging task, it is often simplified for robots by creating demonstrations from the first-person perspective. Creating these demonstrations allows for an easier imitation but requires more effort. Therefore, we introduce a novel diffusion model that enables the robot to learn from the third-person demonstrations directly by learning to generate the first-person perspective from the third-person perspective. The model translates the size and rotations of objects and the environment between the two perspectives. This allows us to utilise the benefits of easy-to-produce third-person demonstrations and easy-to-imitate first-person demonstrations.