CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers

J Zhang, H Liu, K Yang, X Hu, R Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Scene understanding based on image segmentation is a crucial component of autonomous
vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting …

Delivering arbitrary-modal semantic segmentation

J Zhang, R Liu, H Shi, K Yang, S Reiß… - Proceedings of the …, 2023 - openaccess.thecvf.com
Multimodal fusion can make semantic segmentation more robust. However, fusing an
arbitrary number of modalities remains underexplored. To delve into this problem, we create …

Source-free depth for object pop-out

Z Wu, DP Paudel, DP Fan, J Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Depth cues are known to be useful for visual perception. However, direct measurement of
depth is often impracticable. Fortunately, though, modern learning-based methods offer …

Dformer: Rethinking rgbd representation learning for semantic segmentation

B Yin, X Zhang, Z Li, L Liu, MM Cheng… - ar**
X Liu, X Yuan, Q Zhu, Y Wang, M Feng… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Estimating the 6-D pose of an object is a vital and challenging task for robot vision systems
in industrial robotic gras**. With the wide use of 3-D cameras, the additional acquired …

Depth-adapted CNNs for RGB-D semantic segmentation

Z Wu, G Allibert, C Stolz, C Ma… - arxiv preprint arxiv …, 2022 - arxiv.org
Recent RGB-D semantic segmentation has motivated research interest thanks to the
accessibility of complementary modalities from the input side. Existing works often adopt a …

Modality-guided subnetwork for salient object detection

Z Wu, G Allibert, C Stolz, C Ma… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
Recent RGBD-based models for saliency detection have attracted research attention. The
depth clues such as boundary clues, surface normal, shape attribute, etc., contribute to the …