Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

• URL: http://arxiv.org/abs/2605.04035v2
• Date: Fri, 08 May 2026 10:12:59 GMT
• Title: Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
• Abstract summary: HeadsUp is a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups.<n>We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets.
• Score: 29.00521374069166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.

Related papers

• Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation [58.92622703334976]
  High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans.<n>We learn both conditional and unconditional 3D head models from randomly sampled 2D images alone.<n>We introduce MVCHead, a single-shot state space model that enforces multi-view consistency directly in the 3D representation.
  arXiv  Detail & Related papers  (2026-05-24T19:09:15Z)
• TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling [52.87836237427514]
  Photoreal avatars are seen as a key component in emerging applications in telepresence, extended reality, and entertainment.<n>We present a new high-detail 3D head avatar model that improves upon the state of the art.
  arXiv  Detail & Related papers  (2025-05-08T22:10:27Z)
• SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets [72.26350984924129]
  We propose a latent space generation paradigm for 3D human digitization.<n>We transform the ill-posed low-to-high-dimensional mapping problem into a learnable distribution shift.<n>We employ the multi-view optimization approach combined with synthetic data to construct the HGS-1M dataset.
  arXiv  Detail & Related papers  (2025-04-09T15:38:18Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• AugGS: Self-augmented Gaussians with Structural Masks for Sparse-view 3D Reconstruction [9.953394373473621]
  Sparse-view 3D reconstruction is a major challenge in computer vision.<n>We propose a self-augmented two-stage Gaussian splatting framework enhanced with structural masks for sparse-view 3D reconstruction.<n>Our approach achieves state-of-the-art performance in perceptual quality and multi-view consistency with sparse inputs.
  arXiv  Detail & Related papers  (2024-08-09T03:09:22Z)
• VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset [18.62716110331954]
  We introduce method -- a large-scale synthetic dataset generated with diffusion models for human head detection and 3D mesh estimation.<n>Our dataset comprises over 1 million high-resolution images, each annotated with detailed 3D head meshes, facial landmarks, and bounding boxes.<n>Using this dataset, we introduce a new model architecture capable of simultaneous head detection and head mesh reconstruction from a single image in a single step.
  arXiv  Detail & Related papers  (2024-07-25T17:58:17Z)
• GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction [47.113910048252805]
  High-fidelity 3D human head avatars are crucial for applications in VR/AR, digital human, and film production. Recent advances have leveraged morphable face models to generate animated head avatars, representing varying identities and expressions. We introduce 3D Gaussian Parametric Head Model, which employs 3D Gaussians to accurately represent the complexities of the human head.
  arXiv  Detail & Related papers  (2024-07-21T06:03:11Z)
• GGHead: Fast and Generalizable 3D Gaussian Heads [48.967905053963385]
  3D GANs struggle to scale to generate samples at high resolutions due to their relatively slow train and render speeds. We propose Generative Gaussian Heads (GGHead), which adopts the recent 3D Gaussian Splatting representation within a 3D GAN framework. We demonstrate real-time generation and rendering of high-quality 3D-consistent heads at $10242$ resolution for the first time.
  arXiv  Detail & Related papers  (2024-06-13T17:54:38Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos [47.94545609011594]
  We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. Our hybrid pipeline combines the geometry prior and dynamic tracking of a 3DMM with a neural radiance field to achieve fine-grained control and photorealism.
  arXiv  Detail & Related papers  (2023-04-04T01:10:04Z)
• Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation [56.267877301135634]
  Current full head generation methods require a large number of 3D scans or multi-view images to train the model. We propose Head3D, a method to generate full 3D heads with limited multi-view images. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations.
  arXiv  Detail & Related papers  (2023-03-28T11:12:26Z)
• Learning Neural Parametric Head Models [7.679586286000453]
  We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. We capture a person's identity in a canonical space as a signed distance field (SDF), and model facial expressions with a neural deformation field. Our representation achieves high-fidelity local detail by introducing an ensemble of local fields centered around facial anchor points.
  arXiv  Detail & Related papers  (2022-12-06T05:24:42Z)

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.