MarrNet: 3D Shape Reconstruction via 2.5D Sketches

NeurIPS 2017 Jiajun WuYifan WangTianfan XueXingyuan SunWilliam T FreemanJoshua B Tenenbaum

3D object reconstruction from a single image is a highly under-determined problem, requiring strong prior knowledge of plausible 3D shapes. This introduces challenges for learning-based approaches, as 3D object annotations are scarce in real images... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
3D Shape Retrieval Pix3D MarrNet [email protected] 0.42 # 2
[email protected] 0.71 # 2
[email protected] 0.51 # 2
[email protected] 0.78 # 2
[email protected] 0.57 # 2
[email protected] 0.64 # 2