GSExplorer: Interactive World Generation with a Persistent 3DGS World State
cs.CV, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-18
Terminology
Sources
- LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation
- ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
- Depth Anything 3: Recovering the Visual Space from Any Views
- DreamX-World 1.0: A General-Purpose Interactive World Model
- Wan: Open and Advanced Large-Scale Video Generative Models
- Latent Spatial Memory for Video World Models
- NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
- Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- AdaGS: Confidence-Gated Diffusion Adaptation for Unposed Sparse-View 3D Gaussian Reconstruction
- MMGS: 10$\times$ Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking
- UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
- Stereo Magnification: Learning View Synthesis using Multiplane Images
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