Media Summary: In this paper, we propose VideoScene that distills the Introducing UniVidX, a unified multimodal framework designed to leverage the powerful generative priors of pre-trained [CVPR 2026] SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation
Brian Chao Foveated Diffusion Efficient Spatially Adaptive Image And Video Generation - Detailed Analysis & Overview
In this paper, we propose VideoScene that distills the Introducing UniVidX, a unified multimodal framework designed to leverage the powerful generative priors of pre-trained [CVPR 2026] SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation CVPR 2023: Guided Depth Super-Resolution by Deep Anisotropic Diffusion We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser is applicable to variousĀ ...
![Hierarchical Patch Diffusion Models for High-Resolution Video Generation [CVPR 2024]](https://i.ytimg.com/vi/bFDu51XPABI/mqdefault.jpg)
![[CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step](https://i.ytimg.com/vi/pPATpONMbXg/mqdefault.jpg)
![[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Video Super-Resolution](https://i.ytimg.com/vi/b9J3lqiKnLM/mqdefault.jpg)
![[CVPR 2023 Talk] SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field.](https://i.ytimg.com/vi/AfAR-PoZ8SM/mqdefault.jpg)
![[CVPR 2026] SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation](https://i.ytimg.com/vi/WhxBM8vRuc8/mqdefault.jpg)
