The paper introduces JOG3R, a unified model that enhances video generation and camera pose estimation, demonstrating improved accuracy in 3D awareness through fine-tuning and feature repurposing.

https://arxiv.org/abs//2501.01409

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers