HD-VGGT: High-Resolution Visual Geometry Transformer

Tianrun Chen; Yuanqi Hu; Yidong Han; Hanjie Xu; Deyi Ji; Qi Zhu; Chunan Yu; Xin Zhang

cs.CVMar 28, 2026

HD-VGGT: High-Resolution Visual Geometry Transformer

Authors: Tianrun Chen, Yuanqi Hu, Yidong Han, Hanjie Xu, Deyi Ji, Qi Zhu, Chunan Yu, Xin Zhang, +6 more

Organizations: KOKONI 3D, Moxin Technology · Zhejiang University · Huzhou University · Univeristy of Science and Technology of China · Nanjing University of Science and Technology · Huawei · Tongji University

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.

Figures & tables

Figure 1: Overview of the HD-VGGT architecture. A low-resolution branch first computes a coarse 3D feature volume. A high-resolution branch then uses a learned feature upsampler guided by the high-resolution image to produce detailed features, which are processed by a lightweight refiner transformer to yield the final high-fidelity output.

Figure 2: Qualitative comparison of monocular depth estimation. Our method produces more accurate and detailed results, which are indicated by dotted boxes

Figure 3: Qualitative comparison of Point map reconstruction.

Method	RealEstate10K (mixed, static)			Sintel (outdoor, dynamic)			TUM-dynamics (indoor, dynamic)
Method	RRA@30 $\uparrow$	RTA@30 $\uparrow$	AUC@30 $\uparrow$	ATE $\downarrow$	RPE t $\downarrow$	RPE r $\downarrow$	ATE $\downarrow$	RPE t $\downarrow$	RPE r $\downarrow$
Fast3R [ yang2025fast3r ]	99.05	81.86	61.68	0.371	0.298	13.75	0.090	0.101	1.425
CUT3R [ wang2025cut3r ]	99.82	95.10	81.47	0.217	0.070	0.636	0.047	0.015	0.451
FLARE [ zhang2025flare ]	99.69	95.23	80.01	0.207	0.090	3.015	0.026	0.013	0.475
VGGT [ vggt ]	99.97	93.13	77.62	0.167	0.062	0.491	0.012	0.010	0.312
$\pi^{3}$ [ wang2025pi ]	99.99	95.62	85.90	0.074	0.040	0.282	0.014	0.009	0.312

Table 1: Camera pose estimation on RealEstate10K, Sintel, and TUM-dynamics. Our method demonstrates robust and accurate pose estimation.

Method	Pose AUC $\uparrow$ (@10)	Pose AUC $\uparrow$ (@30)
DUSt3R [ dust3r ]	70.1	76.7
MASt3R [ leroy2024mast3r ]	78.2	81.8
VGGT [ vggt ]	83.3	88.2
HD-VGGT (Ours)	86.5	90.4

Table 2: Comparison of camera pose estimation on CO3Dv2. Metrics are Pose AUC

\uparrow

10^{\circ}

and

30^{\circ}

thresholds.

	7-Scenes (scene)				NRGBD (scene)				DTU (object)
Method	Acc. (cm) $\downarrow$		Comp. (cm) $\downarrow$		Acc. (cm) $\downarrow$		Comp. (cm) $\downarrow$		Acc. (cm) $\downarrow$		Comp. (cm) $\downarrow$
	Mean	Med.	Mean	Med.	Mean	Med.	Mean	Med.	Mean	Med.	Mean	Med.
Fast3R [ yang2025fast3r ]	9.6	6.5	14.5	9.3	13.5	9.1	16.3	10.4	334.0	191.9	292.9	112.5
CUT3R [ wang2025cut3r ]	9.4	5.1	10.1	5.0	10.4	4.1	7.9	3.1	474.2	260.0	340.0	131.6
FLARE [ zhang2025flare ]	8.5	5.8	14.2	10.4	5.3	2.4	5.1	2.5	254.1	146.8	317.4	142.0
VGGT [ vggt ]	4.6	2.6	5.7	3.4	5.1	2.9	6.6	3.8	133.8	77.9	189.6	99.2

Table 3: Point map reconstruction on 7-Scenes, NRGBD, and DTU. Our HD-VGGT sets a new state-of-the-art across all benchmarks.

Method	ScanNet		NYUv2
Method	AbsRel $\downarrow$	$\delta_{1}$ $\uparrow$	AbsRel $\downarrow$	$\delta_{1}$ $\uparrow$
DUSt3R [ dust3r ]	0.081	0.909	0.143	0.814
MASt3R [ leroy2024mast3r ]	0.110	0.865	0.115	0.848
VGGT [ vggt ]	0.056	0.951	0.062	0.969
$\pi^{3}$ [ wang2025pi ]	0.054	0.956	0.038	0.986
WorldMirror [ liu2025worldmirror ]	0.052	0.957	0.063	0.968

Table 4: Monocular depth estimation on ScanNet and NYUv2.

Method	Depth Abs Rel $\downarrow$ (w/ GT Pose)	Depth Abs Rel $\downarrow$ (w/o GT Pose)
DUSt3R [ dust3r ]	0.145	0.182
MASt3R [ leroy2024mast3r ]	0.131	0.165
VGGT [ vggt ]	0.119	0.140
HD-VGGT (Ours)	0.102	0.121

Table 5: Monocular Depth estimation on ScanNet under different pose conditions. Metrics are Abs Rel

\downarrow

evaluated with and without ground-truth (GT) poses.

Explore similar work

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
May 14, 2026David Huang, Guile Wu, Chengjie Huang +23D ViTs Multi-View 3D Reconstruction
Huawei Noah’s Ark Lab · University of Toronto · Foundation Model Department, Huawei
GGPT: Geometry Grounded Point Transformer
Mar 11, 2026Yutong Chen, Yiming Wang, Xucong Zhang +2Sparse-View 3D Reconstruction Feed-Forward 3D Reconstruction
ETH Zurich · Delft University of Technology
MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
Mar 2, 2026Leo Kaixuan Cheng, Abdus Shaikh, Ruofan Liang +33D Reconstruction Multi-View 3D Reconstruction
University of Toronto · Vector Institute

May 14, 2026J/K move · Enter open · S save

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

David Huang, Guile Wu, Chengjie Huang, Bingbing Liu+1

Huawei Noah’s Ark Lab · University of Toronto · Foundation Model Department, Huawei

3D ViTs Multi-View 3D Reconstruction Efficient ViTs Sparse Attention Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single forward pass. However, most existing methods struggle to achieve a balance between reconstruction quality and computational efficiency, which limits their scalability and efficiency. Although some efficient visual geometry transformers have recently emerged, they typically use the same sparsity ratio across layers and frames and lack mechanisms to adaptively learn representative tokens to capture global relationships, leading to suboptimal performance. In this work, we propose TurboVGGT, a novel approach that employs an efficient visual geometry transformer with adaptive alternating attention for fast multi-view 3D reconstruction. Specifically, TurboVGGT employs an end-to-end trainable framework that leverages adaptive sparse global attention guided by adaptive sparsity selection to capture global relationships across frames and uses frame attention to aggregate local details within each frame. In the adaptive sparse global attention, TurboVGGT adaptively learns representative tokens with varying sparsity levels for global geometry modeling, considering that token importance varies across frames, different attention layers operate on tokens at different levels of abstraction, and global dependencies rely on structurally informative regions. Extensive experiments on multiple 3D reconstruction benchmarks demonstrate that TurboVGGT achieves fast multi-view reconstruction while maintaining competitive reconstruction quality compared with state-of-the-art methods.

Abstract

Explore similar work

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

GGPT: Geometry Grounded Point Transformer

MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry