UGG: Unified Generative Geometry Model
cs.CV, cs.LG, cs.RO
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Motus: A Unified Latent Action World Model
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Virtual KITTI 2
- Large Video Planner Enables Generalizable Robot Control
- WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control
- FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
- Wan: Open and Advanced Large-Scale Video Generative Models
- SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
- EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
- DUSt3R: Geometric 3D Vision Made Easy
- Video World Models with Long-term Spatial Memory
- NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
- World Action Models are Zero-shot Policies
- NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
- Inference-time Scaling of Diffusion Models through Classical Search
- Stable Virtual Camera: Generative View Synthesis with Diffusion Models
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