GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion

• URL: http://arxiv.org/abs/2606.27659v1
• Date: Fri, 26 Jun 2026 02:31:06 GMT
• Title: GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion
• Abstract summary: GeoFace is a geometry-constrained multi-view diffusion framework for consistent face generation from a single input.<n>Experiments on RenderMe-360 and NeRSemble demonstrate that GeoFace consistently outperforms existing methods in both visual quality and cross-view geometric consistency.
• Score: 36.691978700341515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present GeoFace, a geometry-constrained multi-view diffusion framework for consistent face generation from a single input. % While recent multi-view diffusion models achieve photorealistic synthesis at the per-view level, they lack an explicit mechanism to enforce a shared 3D structure across views, often leading to inconsistent geometry across viewpoints. To address this, GeoFace proposes a unified dual-stream framework for joint generation of multi-view RGB images and 3D face geometry, where the appearance and geometry streams interact through shared attention layers. To encourage the two streams to mutually constrain each other, we introduce a geometry-guided attention alignment loss that supervises the cross-attention between appearance and geometry tokens with 3D-consistent correspondences, enabling the appearance stream to correctly reference pose-invariant geometric cues for robust alignment across viewpoints. Geometry is represented as a canonical UV position map, derived from a FLAME mesh fitted to multi-view observations, serving as a view-invariant shared constraint across all generated views. Experiments on RenderMe-360 and NeRSemble demonstrate that GeoFace consistently outperforms existing methods in both visual quality and cross-view geometric consistency, facilitating more efficient 3D reconstruction.

Related papers

• ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views [9.257489669927624]
  ReconSplat is a feed-forward model for 3D scene reconstruction.<n>It provides both geometrically aligned novel views and sharp depth estimates.<n>It produces both photorealistic novel views and accurate depth maps on real-world benchmarks.
  arXiv  Detail & Related papers  (2026-08-28T21:53:58Z)
• Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction [56.51413081953813]
  SurfSVR is a novel sparse voxel reconstruction paradigm that treats 2D surface priors as explicit 3D geometric regularizers.<n>It consistently improves sparse voxel reconstruction across scenes with substantially different visibility and geometry characteristics.
  arXiv  Detail & Related papers  (2026-08-12T11:25:31Z)
• Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction [44.54907293631917]
  Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap.<n>We propose VGGD, a visual geometry foundation-aware 3D Gaussian Splatting framework for feed-forward surround-view driving reconstruction.
  arXiv  Detail & Related papers  (2026-08-11T09:04:33Z)
• World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible [34.47550981952829]
  We introduce World Tracing, a generative pixel-aligned geometry representation that predicts 3D points aligned with observed pixels.<n>For each input pixel, World Tracing predicts an ordered stack of camera-space 3D points, where the first layer represents the visible surface.<n>We instantiate this representation with a world-tracing diffusion transformer, WT-DiT, which treats multiple geometry layers as separate denoising tokens.
  arXiv  Detail & Related papers  (2026-06-11T17:52:48Z)
• IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation [76.36174247570716]
  We propose IVGT, an Implicit Visual Geometry Transformer that implicitly models continuous and coherent geometry from pose-free multi-view images.<n> IVGT learns a continuous neural scene representation in a canonical coordinate system and supports continuous spatial queries at any 3D positions.<n>It allows direct extraction of continuous and coherent surface geometry, enabling rendering of RGB images, depth maps, and surface normal maps from arbitrary viewpoints.
  arXiv  Detail & Related papers  (2026-05-15T17:59:57Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis [73.97869945427645]
  GeoNVS is a novel-view synthesizer that enhances both geometric fidelity and camera controllability through explicit 3D geometric guidance.<n>GS-Adapter lifts input-view diffusion features into 3D Gaussian representations, and adaptively fuses them with diffusion features to correct geometrically inconsistent representations.<n>Experiments across 9 scenes and 18 settings demonstrate state-of-the-art performance, achieving 11.3% and 14.9% improvements over SEVA and CameraCtrl.
  arXiv  Detail & Related papers  (2026-03-16T08:23:00Z)
• Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations [18.442834011472005]
  A fundamental challenge in text-to-3D face generation is achieving high-quality geometry.<n>We introduce the Spherical Geometry Representation, a novel face representation that anchors geometric signals to uniform spherical coordinates.<n>We then introduce Spherical Diffusion Geometry, a conditional diffusion framework built upon this 2D map.
  arXiv  Detail & Related papers  (2026-01-19T20:15:45Z)
• Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion [57.09673862519791]
  This paper introduces textbfJGA-LBD, a novel framework that unifies the modeling of geometry and appearance into a joint latent representation.<n> Experiments demonstrate that JGA-LBD outperforms current state-of-the-art approaches in terms of both geometry fidelity and appearance quality.
  arXiv  Detail & Related papers  (2026-01-01T12:48:56Z)
• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• Multimodal Conditional 3D Face Geometry Generation [17.262213841207338]
  We demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts.<n>Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain.
  arXiv  Detail & Related papers  (2024-07-01T08:25:59Z)

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.