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

• URL: http://arxiv.org/abs/2505.17590v2
• Date: Mon, 23 Jun 2025 16:26:46 GMT
• Title: CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
• Authors: Florian Barthel, Wieland Morgenstern, Paul Hinzer, Anna Hilsmann, Peter Eisert,
• Abstract summary: 3D GANs based on 3D Gaussian splatting have been proposed for high quality synthesis of human heads.<n>Existing methods stabilize training and enhance rendering quality from steep viewpoints by conditioning the random latent vector on the current camera position.<n>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.
• Score: 10.207899254360374
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 $2048^2$. 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/

Related papers

• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• 3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning [19.763523500564542]
  CHASE is a novel framework that achieves dense-input-level performance using only sparse inputs. We introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set. While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets.
  arXiv  Detail & Related papers  (2024-08-19T02:46:23Z)
• GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
  We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view. The model learns to generate 3D objects represented by sets of GS ellipsoids. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
  arXiv  Detail & Related papers  (2024-07-05T03:43:08Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus [56.45194233357833]
  We propose DoGaussian, a method that trains 3DGS distributedly. Our method accelerates the training of 3DGS by 6+ times when evaluated on large-scale scenes.
  arXiv  Detail & Related papers  (2024-05-22T19:17:58Z)
• Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting [55.71424195454963]
  Spec-Gaussian is an approach that utilizes an anisotropic spherical Gaussian appearance field instead of spherical harmonics. Our experimental results demonstrate that our method surpasses existing approaches in terms of rendering quality. This improvement extends the applicability of 3D GS to handle intricate scenarios with specular and anisotropic surfaces.
  arXiv  Detail & Related papers  (2024-02-24T17:22:15Z)
• Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos [33.779636707618785]
  We introduce Rig3DGS to create controllable 3D human portraits from casual smartphone videos. Key innovation is a carefully designed deformation method which is guided by a learnable prior derived from a 3D morphable model. We demonstrate the effectiveness of our learned deformation through extensive quantitative and qualitative experiments.
  arXiv  Detail & Related papers  (2024-02-06T05:40:53Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.