How I Study AI - Learn AI Papers & Lectures the Easy Way

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Intermediate

Hongyuan Chen, Xingyu Chen et al.Jan 20arXiv

Motion 3-to-4 turns a single regular video into a moving 3D object over time (a 4D asset) by first getting the object’s shape and then figuring out how every part moves.

#4D synthesis#monocular video#motion reconstruction

V-DPM: 4D Video Reconstruction with Dynamic Point Maps

Intermediate

Edgar Sucar, Eldar Insafutdinov et al.Jan 14arXiv

V-DPM is a new way for AI to turn a short video into a moving 3D world, capturing both the shape and the motion of everything in it.

#Dynamic Point Maps#4D reconstruction#scene flow

InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion

Intermediate

Hoiyeong Jin, Hyojin Jang et al.Dec 19arXiv

InsertAnywhere is a two-stage system that lets you add a new object into any video so it looks like it was always there.

#video object insertion#4D scene geometry#diffusion video generation

Papers3

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

V-DPM: 4D Video Reconstruction with Dynamic Point Maps

InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion