# CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis

arXiv: https://arxiv.org/abs/2505.17590 · HTML: https://mlsanity.com/paper/2505.17590/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [3D Shape Induction from 2D Views of Multiple Objects](https://mlsanity.com/paper/1612.05872/) (2016)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circ](https://mlsanity.com/paper/2303.13071/) (2023)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [GIRAFFE HD: A High-Resolution 3D-aware Generative Model](https://mlsanity.com/paper/2203.14954/) (2022)
- [GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds](https://mlsanity.com/paper/2206.07255/) (2022)
- [Gaussian Shell Maps for Efficient 3D Human Generation](https://mlsanity.com/paper/2311.17857/) (2023)
- [GGHead: Fast and Generalizable 3D Gaussian Heads](https://mlsanity.com/paper/2406.09377/) (2024)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video](https://mlsanity.com/paper/2411.15604/) (2024)
- [Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation](https://mlsanity.com/paper/2401.04728/) (2024)
- [Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing](https://mlsanity.com/paper/2312.03763/) (2023)

## Built on by (most cited first, 6 of 6)

- [Drop-In Perceptual Optimization for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.23297/) (2026)
- [Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation](https://mlsanity.com/paper/2605.25220/) (2026)
- [HeadLighter: Disentangling Illumination in Generative 3D Gaussian Heads via Lightstage Captures](https://mlsanity.com/paper/2601.02103/) (2026)
- [COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing](https://mlsanity.com/paper/2605.24114/) (2026)
- [SplitAvatar: One-shot Head Avatar with Autoregressive Gaussian Splitting](https://mlsanity.com/paper/2605.25751/) (2026)
- [One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars](https://mlsanity.com/paper/2610.02207/) (2026)

## Abstract (arXiv)

Recently, 3D GANs based on 3D Gaussian splatting have been proposed for high quality synthesis of human heads. However, existing methods stabilize training and enhance rendering quality from steep viewpoints by conditioning the random latent vector on the current camera position. This compromises 3D consistency, as we observe significant identity changes when re-synthesizing the 3D head with each camera shift. Conversely, fixing the camera to a single viewpoint yields high-quality renderings for that perspective but results in poor performance for novel views. Removing view-conditioning typically destabilizes GAN training, often causing the training to collapse. In response to these challenges, we introduce CGS-GAN, a novel 3D Gaussian Splatting GAN framework that enables stable training and high-quality 3D-consistent synthesis of human heads without relying on view-conditioning. To ensure training stability, we introduce a multi-view regularization technique that enhances generator convergence with minimal computational overhead. Additionally, we adapt the conditional loss used in existing 3D Gaussian splatting GANs and propose a generator architecture designed to not only stabilize training but also facilitate efficient rendering and straightforward scaling, enabling output resolutions up to 20482. To evaluate the capabilities of CGS-GAN, we curate a new dataset derived from FFHQ. This dataset enables very high resolutions, focuses on larger portions of the human head, reduces view-dependent artifacts for improved 3D consistency, and excludes images where subjects are obscured by hands or other objects. As a result, our approach achieves very high rendering quality, supported by competitive FID scores, while ensuring consistent 3D scene generation. Check our our project page here: https://fraunhoferhhi.github.io/cgs-gan/