# 3D-Aware Multi-Class Image-to-Image Translation with NeRFs Source: [3D-Aware Multi-Class Image-to-Image Translation with NeRFs]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:29:58.828Z Authors: Senmao Li, Joost van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang Published: 2023-03-27T08:54:51.000Z ## Abstract Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multi-class image-to-image (3D-aware I2I) translation. Naively using 2D-I2I translation methods suffers from unrealistic shape/identity change. To perform 3D-aware multi-class I2I translation, we decouple this learning process into a multi-class 3D-aware GAN step and a 3D-aware I2I translation step. In the first step, we propose two novel techniques: a new conditional architecture and an effective training strategy. In the second step, based on the well-trained multi-class 3D-aware GAN architecture, that preserves view-consistency, we construct a 3D-aware I2I translation system. To further reduce the view-consistency problems, we propose several new techniques, including a U-net-like adaptor network design, a hierarchical representation constrain and a relative regularization loss. In extensive experiments on two datasets, quantitative and qualitative results demonstrate that we successfully perform 3D-aware I2I translation with multi-view consistency. ## 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. - [Image-to-Image Translation on CelebA-HQ gender as class (test)](): Image-to-Image Translation; CelebA-HQ gender as class (test); TC: 3.743. - [3D-aware Image-to-Image Translation on AFHQ (test)](): 3D-aware Image-to-Image Translation; AFHQ (test); TC: 2.067. - [3D-aware Image-to-Image Translation on CelebA-HQ (test)](): 3D-aware Image-to-Image Translation; CelebA-HQ (test); TC Score: 3.743. - [Image-to-Image Translation on AFHQ 3 classes (test)](): Image-to-Image Translation; AFHQ 3 classes (test); TC: 2.067. ## Original sources and implementation [Original paper]() [PDF]()