Improve 3D object segmentation using transformers directly on point clouds with Mask3D

Improve 3D object segmentation using transformers directly on point clouds with Mask3D

Mask3D for 3D Semantic Instance Segmentation

arXiv paper abstract https://arxiv.org/abs/2210.03105v1

arXiv PDF paper https://arxiv.org/pdf/2210.03105v1.pdf

GitHub https://github.com/jonasschult/mask3d

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.

... propose the first Transformer-based approach for 3D semantic instance segmentation ... to directly predict instance masks from 3D point clouds.

In ... Mask3D .. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales.

Combined with point features, the instance queries directly yield all instance masks in parallel.

Mask3D has several advantages over current state-of-the-art approaches, since it neither relies on (1) voting schemes which require hand-selected geometric properties (such as centers) nor (2) geometric grouping mechanisms requiring manually-tuned hyper-parameters (e.g. radii) and (3) enables a loss that directly optimizes instance masks.

Mask3D sets a new state-of-the-art on ScanNet test ...

Please like and share this post if you enjoyed it using the buttons at the bottom! Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact Web site with my other posts by category https://morrislee1234.wixsite.com/website LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning