A unified, feed-forward model integrating the MapAnything 3D reconstruction backbone with Mask2Former for multi-view consistent panoptic segmentation. This approach provides feature-rich and metric accurate semantic maps for indoor robot navigation while eliminating the need for posed inputs and costly test-time optimization.
deep-neural-networks computer-vision 3d-reconstruction 3d-computer-vision geometric-deep-learning scene-understanding panoptic-segmentation transformer-architecture scannet-dataset transformers-models vision-transformer mapanything multi-view-reconstruction mask2former scannetpp
-
Updated
Apr 13, 2026