3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation

ECCV 2018 Angela DaiMatthias Nießner

We present 3DMV, a novel method for 3D semantic scene segmentation of RGB-D scans in indoor environments using a joint 3D-multi-view prediction network. In contrast to existing methods that either use geometry or RGB data as input for this task, we combine both data modalities in a joint, end-to-end network architecture... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Scene Segmentation ScanNet 3DMV Average Accuracy 75.0% # 1
Semantic Segmentation ScanNet 3DMV 3DIoU 0.484 # 6