DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision.
Lu LingYichen ShengZhi TuWentian ZhaoCheng XinKun WanLantao YuQianyu GuoZixun YuYawen LuXuanmao LiXingpeng SunRohan AshokAniruddha MukherjeeHao KangXiangrui KongGang HuaTianyi ZhangBedrich BenesAniket BeraPublished in: CoRR (2023)
Keyphrases
- deep learning
- unsupervised learning
- restricted boltzmann machine
- machine learning
- unsupervised feature learning
- video sequences
- vision system
- mental models
- computer vision
- multiple images
- image sequences
- single image
- weakly supervised
- deep architectures
- input image
- semi supervised
- domain specific
- data points
- object detectors