# HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting

Source: [HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting](<https://www.sota2.com/research/paper/68fa74871e209131cea62395>)

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

Data updated: 2025-10-26T03:11:37.234Z

Authors: Wenquan Lu, Yufei Xu, Jing Zhang, Chaoyue Wang, Dacheng Tao

Published: 2023-11-29T08:52:08.000Z

## Abstract

Diffusion models have achieved remarkable success in generating realistic images but suffer from generating accurate human hands, such as incorrect finger counts or irregular shapes. This difficulty arises from the complex task of learning the physical structure and pose of hands from training images, which involves extensive deformations and occlusions. For correct hand generation, our paper introduces a lightweight post-processing solution called $\\textbf{HandRefiner}$. HandRefiner employs a conditional inpainting approach to rectify malformed hands while leaving other parts of the image untouched. We leverage the hand mesh reconstruction model that consistently adheres to the correct number of fingers and hand shape, while also being capable of fitting the desired hand pose in the generated image. Given a generated failed image due to malformed hands, we utilize ControlNet modules to re-inject such correct hand information. Additionally, we uncover a phase transition phenomenon within ControlNet as we vary the control strength. It enables us to take advantage of more readily available synthetic data without suffering from the domain gap between realistic and synthetic hands. Experiments demonstrate that HandRefiner can significantly improve the generation quality quantitatively and qualitatively. The code is available at https://github.com/wenquanlu/HandRefiner .

## 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.

- [Glove-to-Hand Video Translation on HandSense (test)](<https://www.sota2.com/research/sota/glove-to-hand-video-translation-on-handsense-test.md>): Glove-to-Hand Video Translation; HandSense (test); FID: 35.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.17957>)

[PDF](<https://arxiv.org/pdf/2311.17957.pdf>)
