# CLIP-based Neural Neighbor Style Transfer for 3D Assets

arXiv: https://arxiv.org/abs/2208.04370 · HTML: https://mlsanity.com/paper/2208.04370/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2022.

## Built on by (most cited first, 5 of 5)

- [Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion](https://mlsanity.com/paper/2303.15780/) (2023)
- [Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details](https://mlsanity.com/paper/2308.16880/) (2023)
- [Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation](https://mlsanity.com/paper/2307.03869/) (2023)
- [CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields](https://mlsanity.com/paper/2404.14967/) (2024)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)

## Abstract (arXiv)

We present a method for transferring the style from a set of images to a 3D object. The texture appearance of an asset is optimized with a differentiable renderer in a pipeline based on losses using pretrained deep neural networks. More specifically, we utilize a nearest-neighbor feature matching loss with CLIP-ResNet50 to extract the style from images. We show that a CLIP- based style loss provides a different appearance over a VGG-based loss by focusing more on texture over geometric shapes. Additionally, we extend the loss to support multiple images and enable loss-based control over the color palette combined with automatic color palette extraction from style images.