S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens
cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Project page: https://s2tok.github.io
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
- Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting
- Depth Anything 3: Recovering the Visual Space from Any Views
- TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
- ZipSplat: Fewer Gaussians, Better Splats
- Helix4D: Complex 4D Mesh Generation
- S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
- 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