HD-VGGT: High-Resolution Visual Geometry Transformer

• URL: http://arxiv.org/abs/2603.27222v1
• Date: Sat, 28 Mar 2026 10:29:07 GMT
• Title: HD-VGGT: High-Resolution Visual Geometry Transformer
• Abstract summary: We introduce HD-VGGT, a dual-branch architecture for efficient and robust high-resolution 3D reconstruction.<n>A low-resolution branch predicts a coarse, globally consistent geometry, while a high-resolution branch refines details via a learned feature upsampling module.<n>To handle unstable tokens, we propose Feature Modulation, which suppresses unreliable features early in the transformer.
• Score: 28.73190234129584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated the ability to infer scene geometry from large collections of images in a single forward pass. However, scaling these models to high-resolution inputs remains challenging: the number of tokens in transformer architectures grows rapidly with both image resolution and the number of views, leading to prohibitive computational and memory costs. Moreover, we observe that visually ambiguous regions, such as repetitive patterns, weak textures, or specular surfaces, often produce unstable feature tokens that degrade geometric inference, especially at higher resolutions. We introduce HD-VGGT, a dual-branch architecture for efficient and robust high-resolution 3D reconstruction. A low-resolution branch predicts a coarse, globally consistent geometry, while a high-resolution branch refines details via a learned feature upsampling module. To handle unstable tokens, we propose Feature Modulation, which suppresses unreliable features early in the transformer. HD-VGGT leverages high-resolution images and supervision without full-resolution transformer costs, achieving state-of-the-art reconstruction quality.

Related papers

• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors [61.34273238077091]
  We present a novel method for generating orbital videos from a single image of an object.<n>Our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-14T05:35:46Z)
• LATTICE: Democratize High-Fidelity 3D Generation at Scale [27.310104395842075]
  LATTICE is a new framework for high-fidelity 3D asset generation.<n> VoxSet is a semi-structured representation that compresses 3D assets into a compact set of latent vectors anchored to a coarse voxel grid.<n>Our method is simple at its core, but supports arbitrary resolution decoding, low-cost training, and flexible inference schemes.
  arXiv  Detail & Related papers  (2025-11-24T03:22:19Z)
• LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning [26.88556500272625]
  We propose a novel 3D variational autoencoder framework built upon unsigned distance fields (UDFs)<n>Our core innovation is a local-to-global architecture that processes the UDF by partitioning it into uniform subvolumes, UBlocks.<n> Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility.
  arXiv  Detail & Related papers  (2025-11-13T07:34:43Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
  We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
  arXiv  Detail & Related papers  (2025-08-05T04:50:29Z)
• SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling [79.56581753856452]
  SparseFlex is a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $10243$ directly from rendering losses.<n>By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.
  arXiv  Detail & Related papers  (2025-03-27T17:46:42Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [38.6438956631446]
  Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. We formulate a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning. We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images.
  arXiv  Detail & Related papers  (2020-04-01T13:52:53Z)

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.