LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences
Paper
•
2412.01292
•
Published
•
12
Shuailei Ma
Xiaomabufei
AI & ML interests
text-to-image generation, novel view synthesis, image-to-video generation, object detection, human-object interaction detection
Recent Activity
liked
a Space
27 days ago
black-forest-labs/FLUX.1-canny-dev
updated
a model
28 days ago
Xiaomabufei/lumos
liked
a dataset
28 days ago
FanLu31/CompreCap
Organizations
None yet