VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors

Yuhang Ming; Tingkang Xi; Xingrui Yang; Lixin Yang; Yong Peng; Cewu Lu; Wanzeng Kong

cs.CVMar 13, 2026

VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors

Authors: Yuhang Ming, Tingkang Xi, Xingrui Yang, Lixin Yang, Yong Peng, Cewu Lu, Wanzeng Kong

Organizations: Shanghai Jiao Tong University, Shanghai, China · Hangzhou Dianzi University, Hangzhou, China · CARDC, Mianyang, China

Abstract

Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent advances in vision foundation models (VFMs) provide transferable generalized priors learned from large-scale data, their scale-ambiguous predictions are incompatible with the scale consistency required by volumetric fusion. To address this gap, we present VFM-Recon, the first attempt to bridge transferable VFM priors with scale-consistent requirements in scene-level neural reconstruction. Specifically, we first introduce a lightweight scale alignment stage that restores multi-view scale coherence. We then integrate pretrained VFM features into the neural volumetric reconstruction pipeline via lightweight task-specific adapters, which are trained for reconstruction while preserving the cross-domain robustness of pretrained representations. We train our model on ScanNet train split and evaluate on both in-distribution ScanNet test split and out-of-distribution TUM RGBD and Tanks and Temples datasets. The results demonstrate that our model achieves state-of-the-art performance across all dataset domains. In particular, on the challenging outdoor Tanks and Temples dataset, our model achieves an F1 score of 73.5 in reconstructed mesh evaluation, substantially outperforming the closest neural volumetric reconstruction competitor, SimpleRecon, with an F1 score of 35.7, as well as the closest VFM competitor, $π^3$ , with an F1 score of 67.0.

Figures & tables

Fig. 1: We present VFM-Recon , a novel framework that enables cross-domain, scale-consistent neural volumetric reconstruction. Existing neural reconstruction methods such as FineRecon [ 6 ] perform well on indoor scenes but struggle under domain shift, while VFMs, taking VGGT [ 11 ] for example, predict plausible point maps, yet lack scale consistency for mesh reconstruction. The radar plot highlights consistent performance gains across ScanNet [ 8 ] , TUM RGBD [ 21 ] , and Tanks and Temples [ 22 ] .

Fig. 2: System Overview. On the top is our VFM-augmented volumetric reconstruction network , and in the bottom is our lightweight scale alignment module . Our system divides the sequence into overlapping submaps and uses VFMs to predict scale-ambiguous depths. It then recovers per-submap scales via feature matching and triangulation, followed by factor-graph global scale optimization. The aligned depths are further refined with a fuse-and-back-projection process and are used as geometric priors for subsequent VFM-augmented neural reconstruction.

Fig. 3: Network Architecture. Details of our adapted VFM-backbone for VFM-augmented volumetric reconstruction network, in which only the MLP adapter is trainable.

Method	Venue	Abs.Rel. $\downarrow$	Abs.Diff. $\downarrow$	Sq.Rel. $\downarrow$	$\delta<{1.05}$ $\uparrow$	$\delta<{1.25}$ $\uparrow$	Comp. $\uparrow$
VoRTX [ 24 ]	3DV’21	6.1	9.4	3.7	79.0	95.0	96.1
NeuralRecon [ 5 ]	CVPR’21	6.5	10.6	3.1	-	94.8	90.9
SimpleRecon [ 25 ]	ECCV’22	4.3	8.9	1.3	70.2	98.1	-
FineRecon [ 6 ]	ICCV’23	5.5	8.5	3.8	82.8	95.8	97.2
DG-Recon [ 20 ]	ICCV’23	6.2	9.9	4.0	-	93.7	96.6
Zuo et al. [ 1 ]	RA-L’23	5.2	8.7	2.5	-	94.8	90.6

TABLE I: 2D Rendered Depth Results on ScanNet [ 8 ] . The best, second best, and third best results are marked in bold , underlined , and italic respectively.

Method	Acc. $\downarrow$	Comp. $\downarrow$	Cham. $\downarrow$	Prec. $\uparrow$	Recall $\uparrow$	F1 $\uparrow$
VoRTX [ 24 ]	5.4	9.0	-	70.8	58.8	64.1
NeuralRecon [ 5 ]	5.4	12.8	-	68.4	47.9	56.2
SimpleRecon [ 25 ]	6.1	5.5	5.8	68.6	65.8	67.1
FineRecon [ 6 ]	5.6	5.4	5.5	76.9	71.3	73.6
DG-Recon [ 20 ]	3.9	6.8	5.4	76.9	63.6	69.4
Zuo et al. [ 1 ]	5.8	11.0	-	66.5	50.5	57.2

TABLE II: 3D Reconstruction Results on ScanNet [ 8 ] . The best, second best, and third best results are marked in bold , underlined , and italic respectively.

Method	TUM RGBD [ 21 ]			Tanks&Temples [ 22 ]
Method	Prec. $\uparrow$	Recall $\uparrow$	F1 $\uparrow$	Prec. $\uparrow$	Recall $\uparrow$	F1 $\uparrow$
VoRTX [ 24 ]	28.0	19.4	22.9	-	-	-
NeuralRecon [ 5 ]	49.4	24.8	32.4	42.6	24.7	30.2
SimpleRecon [ 25 ]	40.0	48.0	43.5	44.4	31.5	35.7
Zuo et al. [ 1 ]	36.9	13.3	19.5	-	-	-
FineRecon [ 6 ]	27.4	32.2	29.6	47.0	26.5	33.1

TABLE III: Cross-Domain Evaluation of Reconstructed Mesh. The best, second best, and third best results are marked in bold , underlined , and italic respectively.

Fig. 4: Qualitative Comparisons. In the in-domain examples (top 2 rows), VFM-Recon is compared with FineRecon [ 6 ] and NeuralRecon [ 5 ] , showing improved structural details such as staircases, table legs, and TV surfaces. In the cross-domain examples (bottom 2 rows), VFM-Recon is compared with FineRecon [ 6 ] and VGGT [ 11 ] , producing more complete structures with fewer fragmented artifacts in challenging outdoor scenes.

Variant	Settings				ScanNet [ 8 ]			Tanks&Temples [ 22 ]
Variant	V.D.	S.A.	D.R.	A.V.	Prec. $\uparrow$	Recall $\uparrow$	F1 $\uparrow$	Prec. $\uparrow$	Recall $\uparrow$	F1 $\uparrow$
Default	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	75.7	73.2	74.3	68.6	73.7	70.1
w/o S.A.	$\checkmark$		$\checkmark$	$\checkmark$	74.5	71.5	72.8	45.5	48.4	45.4
w/o D.R.	$\checkmark$	$\checkmark$		$\checkmark$	76.5	75.4	75.8	59.8	48.3	50.5
w/o S.A.&D.R.	$\checkmark$			$\checkmark$	73.7	71.0	72.3	49.0	32.6	36.0
Adapted VGGT Only				$\checkmark$	75.7	72.2	73.9	42.8	31.6	33.7

TABLE IV: Ablation Studies. V.D. denotes the use of VGGT depth, S.A. and D.R refer to our scale alignment and depth reprojection step respectively, A.V. indicates task-adapted VGGT features. The best, second best, and third best results are marked in bold , underlined , and italic respectively.

3D Reconstruction

3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.

See all 955 papers

VGGT- $Ω$
May 14, 2026Jianyuan Wang, Minghao Chen, Shangzhan Zhang +7Multi-View 3D Reconstruction Dynamic Scene Reconstruction
Visual Geometry Group, University of Oxford · Meta AI · 2Meta AI
Glob3R: Global Structure-from-Motion with 3D Foundation Models
Jul 10, 2026Junyuan Deng, Heng Li, Kejie Qiu +7Bundle Adjustment Multi-View 3D Reconstruction
The Hong Kong University of Science and Technology · Tongyi Lab, Alibaba Group · Nanjing University +1
VGG-T $^3$ : Offline Feed-Forward 3D Reconstruction at Scale
Feb 26, 2026Sven Elflein, Ruilong Li, Sérgio Agostinho +43D Reconstruction Feed-Forward 3D Reconstruction
NVIDIA · Vector Institute · University of Toronto

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

VGGT- $Ω$

Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev+6

Visual Geometry Group, University of Oxford · Meta AI · 2Meta AI

Multi-View 3D Reconstruction Dynamic Scene Reconstruction Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these models scales predictably with model and data size. We do so by introducing VGGT-

Ω

, which substantially improves reconstruction accuracy, efficiency, and capabilities for both static and dynamic scenes. To enable training this model at an unprecedented scale, we introduce architectural changes that improve training efficiency, a high-quality data annotation pipeline that supports dynamic scenes, and a self-supervised learning protocol. We simplify VGGT's architecture by using a single dense prediction head with multi-task supervision and removing the expensive high-resolution convolutional layers. We also use registers to aggregate scene information into a compact representation and introduce register attention, which restricts inter-frame information exchange to these registers, in part replacing global attention. In this way, during training, VGGT-

Ω

uses only about 30% of the GPU memory of its predecessor, allowing us to train with 15x more supervised data than prior work and to leverage vast amounts of unlabeled video data. VGGT-

Ω

achieves strong results for reconstruction of static and dynamic scenes across multiple benchmarks, for example, improving over the previous best camera estimation accuracy on Sintel by 77%. We also show that the learned registers can improve vision-language-action models and support alignment with language, suggesting that reconstruction can be a powerful and scalable proxy task for spatial understanding. Project Page: http://vggt-omega.github.io/

Abstract

3D Reconstruction

Explore similar work

VGGT-ΩΩΩ

Glob3R: Global Structure-from-Motion with 3D Foundation Models

VGG-T3^33: Offline Feed-Forward 3D Reconstruction at Scale

VGGT- $Ω$

VGG-T $^3$ : Offline Feed-Forward 3D Reconstruction at Scale