Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation

• URL: http://arxiv.org/abs/2605.25220v1
• Date: Sun, 24 May 2026 19:09:15 GMT
• Title: Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
• Abstract summary: 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.
• Score: 58.92622703334976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans. Existing methods depend on multi-view datasets, 3D captures, or intermediate 2D view synthesis. In contrast, we learn both conditional and unconditional 3D head models from randomly sampled 2D images alone, without using multi-view data, 3D supervision, or intermediate view generation. We introduce MVCHead, a single-shot state space model that enforces multi-view consistency (MVC) directly in the 3D representation while regressing 3D Gaussians under these constraints. At its core, we propose a Hierarchical State Space (HiSS) block that progressively refines Gaussians from coarse to fine, while capturing long-range dependencies. Within each HiSS block, we modify Mamba's standard unidirectional scan with the proposed Hierarchical Bi-directional State Scan (HiBiSS) that aligns recurrence with the axes along which multi-view inconsistencies are strongest. Finally, we design an SE(3) Multi-view Critic that judges whether a set of self-renders arises from a single underlying 3D configuration, rewarding cross-view pixel alignment without observing real multi-view pairs. MVCHead achieves state-of-the-art perceptual quality, surpasses prior methods in both texture and geometric consistency, and maintains comparable shape consistency. To demonstrate scalability, we release FaceGS-10K, the first large-scale dataset of ready-to-use 3D Gaussian head assets for training and evaluation of 3D head models. Project Page and code: https://humansensinglab.github.io/MVCHead/

Related papers

• 3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis [35.43901502343984]
  3DCarGen is a scalable single-view 3D car generation framework for real-world images.<n>Our approach achieves robust geometric consistency and reconstruction fidelity compared to existing methods.
  arXiv  Detail & Related papers  (2026-06-23T07:44:14Z)
• Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures [29.00521374069166]
  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.
  arXiv  Detail & Related papers  (2026-05-05T17:55:01Z)
• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder [90.8453349494245]
  We present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space.<n>OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods.
  arXiv  Detail & Related papers  (2026-03-17T03:43:37Z)
• RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting [81.66201044236321]
  Estimating 3D human poses from 2D images remains challenging.<n>Recent methods rely on 2D pose estimation combined with 2D-to-3D pose lifting trained on synthetic data.<n>We propose RUMPL, a transformer-based 3D pose lifter that introduces a 3D ray-based representation of 2D keypoints.
  arXiv  Detail & Related papers  (2025-12-17T14:37:27Z)
• PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing [51.56943889042673]
  PercHead is a method for single-image 3D head reconstruction and semantic 3D editing.<n>We develop a unified base model for reconstructing view-consistent 3D heads from a single input image.<n>We highlight the intuitive and powerful 3D editing capabilities of our model through a lightweight, interactive GUI.
  arXiv  Detail & Related papers  (2025-11-04T17:59:15Z)
• Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation [9.325977756516908]
  We consider the problem of disentangling 3D from large vision-language models, which we show on generative 3D portraits.<n>This allows free-form text control of appearance attributes like age, hair style, and glasses, and 3D geometry control of face expression and camera pose.<n>Compared to existing methods, our approach produces portraits with added text and 3D control, where portraits remain consistent when either control is changed.
  arXiv  Detail & Related papers  (2025-06-16T21:26:45Z)
• GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation [24.255633621887988]
  We propose a method that leverages 2D diffusion models' implicit 3D reasoning ability while ensuring 3D consistency.<n>Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation.<n>As a result, our approach simultaneously generates high-quality, multi-view-consistent images and accurate 3D models.
  arXiv  Detail & Related papers  (2025-03-08T09:10:31Z)
• F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting [35.625593119642424]
  This paper tackles the problem of generalizable 3D-aware generation from monocular datasets.<n>We propose a novel feed-forward pipeline based on pixel-aligned Gaussian Splatting.<n>We also introduce a self-supervised cycle-aggregative constraint to enforce cross-view consistency in the learned 3D representation.
  arXiv  Detail & Related papers  (2025-01-12T04:44:44Z)
• EmbodiedSAM: Online Segment Any 3D Thing in Real Time [61.2321497708998]
  Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration.<n>An online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed.
  arXiv  Detail & Related papers  (2024-08-21T17:57:06Z)
• Monocular, One-stage, Regression of Multiple 3D People [105.3143785498094]
  We propose to Regress all meshes in a One-stage fashion for Multiple 3D People (termed ROMP) Our method simultaneously predicts a Body Center heatmap and a Mesh map, which can jointly describe the 3D body mesh on the pixel level. Compared with state-of-the-art methods, ROMP superior performance on the challenging multi-person benchmarks.
  arXiv  Detail & Related papers  (2020-08-27T17:21:47Z)

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.