Objects Can Move: 3D Change Detection by Geometric Transformation Constistency
This addresses the need for AR/VR and robotics applications to identify scene changes, but it is incremental as it builds on existing change detection methods with a novel geometric approach.
The paper tackles the problem of detecting scene changes like object movement in 3D environments by proposing a method that discovers objects based on rigid motion consistency, achieving state-of-the-art performance on the 3RScan dataset.
AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at https://github.com/katadam/ObjectsCanMove.