STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
This work addresses semantic segmentation for robotic or handheld RGBD cameras, offering incremental gains by using unlabeled frames and multi-view information.
The authors tackled semantic segmentation in indoor videos by leveraging multiple views to improve accuracy, achieving state-of-the-art results on NYU-Depth-V2 and SUN3D datasets with general improvements over existing methods.
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene. Particularly in indoor videos such as captured by robotic platforms or handheld and bodyworn RGBD cameras, nearby video frames provide diverse viewpoints and additional context of objects and scenes. To leverage such information, we first compute region correspondences by optical flow and image boundary-based superpixels. Given these region correspondences, we propose a novel spatio-temporal pooling layer to aggregate information over space and time. We evaluate our approach on the NYU--Depth--V2 and the SUN3D datasets and compare it to various state-of-the-art single-view and multi-view approaches. Besides a general improvement over the state-of-the-art, we also show the benefits of making use of unlabeled frames during training for multi-view as well as single-view prediction.