From Video to Digital Twin: An Exploratory Study of World Models and Gaussian Splatting on In-the-Wild Video
cs.CV, cs.GR
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/pikulsomesh/foodbank-spatial-twin
Project page: https://pikulsomesh.github.io/foodbank-spatial-twin
Terminology
Sources
- Grounding Image Matching in 3D with MASt3R
- VGGT: Visual Geometry Grounded Transformer
- FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting
- InstantSplat: Sparse-view Gaussian Splatting in Seconds
- NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
- WildGaussians: 3D Gaussian Splatting in the Wild
- SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting
- CAT3D: Create Anything in 3D with Multi-View Diffusion Models
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- Genie: Generative Interactive Environments
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs