# Putting People in Their Place: Affordance-Aware Human Insertion into Scenes

Source: [Putting People in Their Place: Affordance-Aware Human Insertion into Scenes](<https://www.sota2.com/research/paper/68fa6f271e209131cea44150>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-01T16:55:30.269Z

Authors: Sumith Kulal, Tim Brooks, Alex Aiken, Jiajun Wu, Jimei Yang, Jingwan Lu, Alexei A. Efros, Krishna Kumar Singh

Published: 2023-04-27T17:59:58.000Z

## Abstract

We study the problem of inferring scene affordances by presenting a method for realistically inserting people into scenes. Given a scene image with a marked region and an image of a person, we insert the person into the scene while respecting the scene affordances. Our model can infer the set of realistic poses given the scene context, re-pose the reference person, and harmonize the composition. We set up the task in a self-supervised fashion by learning to re-pose humans in video clips. We train a large-scale diffusion model on a dataset of 2.4M video clips that produces diverse plausible poses while respecting the scene context. Given the learned human-scene composition, our model can also hallucinate realistic people and scenes when prompted without conditioning and also enables interactive editing. A quantitative evaluation shows that our method synthesizes more realistic human appearance and more natural human-scene interactions than prior work.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Person Hallucination on Video-based human insertion dataset 1.0 (test)](<https://www.sota2.com/research/sota/person-hallucination-on-video-based-human-insertion-dataset-1-0-test.md>): Person Hallucination; Video-based human insertion dataset 1.0 (test); FID: 8.39.

- [Scene Hallucination on Video-based human insertion dataset 1.0 (test)](<https://www.sota2.com/research/sota/scene-hallucination-on-video-based-human-insertion-dataset-1-0-test.md>): Scene Hallucination; Video-based human insertion dataset 1.0 (test); FID: 20.268.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2304.14406>)

[PDF](<https://arxiv.org/pdf/2304.14406.pdf>)

[Implementation](<https://sumith1896.github.io/affordance-insertion>)