VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization

Yibin Zhao; Yihan Pan; Yangwen Li; Jun Nan; Jianjun Yi

cs.CVSep 18, 2026

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization

Authors: Yibin Zhao, Yihan Pan, Yangwen Li, Jun Nan, Jianjun Yi

Organizations: East China University of Science and Technology Shanghai, China · Shanghai Open University Shanghai, China

Abstract

Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifacts, while inaccuracies in predicted camera poses can lead to misalignment in novel-view synthesis (NVS). We present VoxelTTO, a feed-forward framework for reconstructing geometrically accurate 3DGS scenes from an arbitrary number of images and optional camera parameters. VoxelTTO aggregates dense image features into a global voxel representation and decodes Gaussians from voxel features, breaking the pixel-to-Gaussian correspondence. To exploit known camera parameters while keeping the pretrained visual foundation model (VFM) parameters frozen, we introduce test-time optimization (TTO) that adapts lightweight LoRA modules using pose supervision. We further replace vanilla 3DGS rasterization with stochastic solid volume rendering during training and inference, improving geometric fidelity. Training updates only the voxel-aligned Gaussian reconstruction modules, requiring 80 GPU hours. Experiments on Replica, Tanks and Temples, and DTU demonstrate improved RGB-D NVS and camera-pose estimation relative to prior methods.

Figures & tables

Figure 1: VoxelTTO directly regresses a geometrically accurate Gaussian-splatting scene from posed images. It precisely aligns camera poses and improves RGB and depth rendering in both input and test views across indoor–outdoor and synthetic–realworld scenes.

Figure 2: Overview of the VoxelTTO pipeline.

Figure 3: Geometric advantages of stochastic solid volume rendering over 3DGS rasterization.

Figure 4: Test-view misalignment after injecting camera parameters.

Figure 5: Qualitative RGB novel-view synthesis results for test views.

Figure 6: Qualitative depth novel-view synthesis results for test views.

Replica Dataset
Method	Input Views					Test Views
	RMSE $\downarrow$	Rel $\downarrow$	$\delta_{1.05}$ $\uparrow$	$\delta_{1.10}$ $\uparrow$	$\delta_{1.25}$ $\uparrow$	RMSE $\downarrow$	Rel $\downarrow$	$\delta_{1.05}$ $\uparrow$	$\delta_{1.10}$ $\uparrow$	$\delta_{1.25}$ $\uparrow$
VolSplat	102.8	30.42	11.88	22.55	46.78	202.2	63.89	0.812	2.443	6.859
MVSplat	216.0	69.26	1.984	3.894	9.261	1649	446.1	11.84	25.77	42.37
AnySplat	33.72	9.582	59.05	76.88	86.14	35.92	10.78	45.43	67.09	89.86
YoNoSplat	23.47	7.281	51.07	75.58	94.78	242.1	78.73	0.304	0.692	2.643

Table 2: Quantitative depth novel-view synthesis results for input and test views.

Table 8

Explore similar work

$\text{VG}^2$ GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
Jun 1, 2026Yibin Zhao, Yihan Pan, Jun Nan +33D Gaussian Splatting Novel View Synthesis
East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China · Shanghai Open University, 288 Guoshun Road, 200433, Shanghai, China · Shanghai Xiaoyuan Innovation Center, 599 Xingmei Road, 200237, Shanghai, China
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
Sep 23, 2025Weijie Wang, Yeqing Chen, Zeyu Zhang +9Multi-View Consistency 3D Gaussian Splatting
Zhejiang University · GigaAI · The Chinese University of Hong Kong +4
VS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views
Sep 11, 2026Yunsu Jeong, Hyuk Heo, Youngsang Kwak +23D Gaussian Splatting Sparse-View 3D Reconstruction
Department of Electrical and Computer Engineering (ECE), Sungkykwan University (SKKU), Suwon 16419, South Korea · Department of Display Convergence Engineering (DCE), SKKU, Suwon 16419, South Korea · AiM Future, Seoul 06804, South Korea +1

Jun 1, 2026J/K move · Enter open · S save

$\text{VG}^2$ GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

Yibin Zhao, Yihan Pan, Jun Nan, Wenli Yang+2

East China University of Science and Technology, 130 Meilong Road, Shanghai, 200237, China · Shanghai Open University, 288 Guoshun Road, 200433, Shanghai, China · Shanghai Xiaoyuan Innovation Center, 599 Xingmei Road, 200237, Shanghai, China

3D Gaussian Splatting Novel View Synthesis Geometric Representation Learning Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

Gaussian splatting has shown strong potential for 3D reconstruction and novel view synthesis. However, most existing methods require accurate camera parameters and per-scene optimization, while feed-forward methods with pixel-aligned Gaussian primitives often suffer from artifacts and non-uniform primitives. In this paper, we propose

\text{VG}^2

GT, a Voxel-Gaussian Splatting Visual Geometry-Grounded Transformer.

\text{VG}^2

GT leverages a frozen pretrained visual foundation model (VFM), incorporates a multi-scale differentiable voxel module to enhance geometric understanding, and directly splits and regresses Gaussian primitive parameters from voxel features. During training, depth maps are supervised through stochastic solid volume rendering, enabling geometrically accurate Gaussian scene reconstruction while keeping the visual foundation model fully frozen. This design enables

\text{VG}^2

GT to be seamlessly plugged into any patch-feature-based VFM, while substantially reducing the required training cost.

\text{VG}^2

GT outperforms current state-of-the-art methods on widely used DTU, Replica, TAT, and ScanNet datasets.

Abstract

Explore similar work

VG2\text{VG}^2VG2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

VS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views

$\text{VG}^2$ GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer