DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given

arXiv:2610.07958 · cs.CV · Submitted 2026-10-06 · Read on arXiv

cs.CV

Submitted: 2026-10-06

Updated: 2026-10-06

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Gaussian Splatting — 1× in this paper · explained in 4 episodes

Sources

• Layer Normalization
• Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions
• Auto-Encoding Variational Bayes
• Depth Anything 3: Recovering the Visual Space from Any Views
• Flow Matching for Generative Modeling
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
• Stereo Magnification: Learning View Synthesis using Multiplane Images

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