VBot Exo2Ego Policy: Lightweight Data Collection and Exocentric-to-Egocentric Video Generation
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
- Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- Sharp Monocular View Synthesis in Less Than a Second
- AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
- DUSt3R: Geometric 3D Vision Made Easy
- VGGT: Visual Geometry Grounded Transformer
- Depth Anything 3: Recovering the Visual Space from Any Views
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
- 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere
- Any4D: Unified Feed-Forward Metric 4D Reconstruction
- TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
- EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh
- ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
- Vista4D: Video Reshooting with 4D Point Clouds
- Manifold4D: Denoising on Point Cloud Rendered Manifolds for Video Re-shooting
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