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

arXiv:2609.21498 · cs.CV · Submitted 2026-09-18 · Read on arXiv

cs.CV

Submitted: 2026-09-18

Updated: 2026-09-18

Code: https://github.com/princeton-vl/infinigen

Project page: https://dl3dv-10k.github.io/DL3DV-10K

Terminology

• Accuracy — 21× in this paper · explained in 1 episode
• Gaussian Splatting — 13× in this paper · explained in 4 episodes
• Conference on Computer Vision and Pattern Recognition — 8× in this paper
• 3D Gaussian Splatting — 7× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Generative AI — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• In European Conference on Computer Vision — 2× in this paper
• 3D Gaussian Splatting (3DGS) — 1× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Feed-forward framework — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data
• MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
• From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
• LoRA: Low-Rank Adaptation of Large Language Models
• QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction
• Depth Anything 3: Recovering the Visual Space from Any Views
• The Replica Dataset: A Digital Replica of Indoor Spaces
• VGGT-$\Omega$
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• Geometry-Grounded Gaussian Splatting
• Learning 3D Reconstruction with Priors in Test Time

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models