SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation.

Changsheng Lv Mengshi Qi Xia Li Zhengyuan Yang Huadong Ma

Published in: AAAI (2024)

Keyphrases

d scene
single image
depth map
image based rendering
planar surfaces
photorealistic
camera parameters
optical flow
scene understanding
scene structure
indoor scenes
scene flow
coordinate frame
ego motion
scene geometry
view dependent
view synthesis
flow estimation
pose estimation