VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
cs.CV, cs.AI, cs.LG
Submitted: 2026-01-30
Updated: 2026-06-07
Project page: https://hongyang-du.github.io/VideoGPA-Website
Terminology
Sources
- First Frame Is the Place to Go for Video Content Customization
- Rethinking Video Generation Model for the Embodied World
- Vidar: Embodied Video Diffusion Model for Generalist Manipulation
- CogVLM2: Visual Language Models for Image and Video Understanding
- Epipolar Geometry Improves Video Generation Models
- NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
- Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
- Cosmos World Foundation Model Platform for Physical AI
- Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
- DanceGRPO: Unleashing GRPO on Visual Generation
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