🌴🌴Direct-a-Video: driving Video Generation🌴🌴

👉Direct-a-Video is a text-to-video generation framework that allows users to individually or jointly control the camera movement and/or object motion. Authors: City University of HK, Kuaishou Tech & Tianjin.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Decoupling camera/object motion in gen-AI
✅Allowing users to independently/jointly control
✅Novel temporal cross-attention for cam motion
✅Training-free spatial cross-attention for objects
✅Driving object generation via bounding boxes

hashtag#artificialintelligence hashtag#machinelearning hashtag#ml hashtag#AI hashtag#deeplearning hashtag#computervision hashtag#AIwithPapers hashtag#metaverse

👉Channel: @MachineLearning_Programming
👉Paper https://arxiv.org/pdf/2402.03162.pdf
👉Project https://direct-a-video.github.io/

🧠 VGGT: Visual Geometry Grounded Transformer

⚡️ Fast, accurate 3D scene understanding from just a few images — no post-processing needed!

🎯 Outputs: camera pose, depth, point cloud & 3D tracking
🔥 Boosts tasks like view synthesis & non-rigid tracking

📄 Read the paper
💻 Code on GitHub

#AI #3D #Transformer #VGGT #ComputerVision

✅ @MachineLearning_Programming