EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
For 3D vision researchers, EvObj enables unsupervised segmentation without scene-level supervision, addressing a key bottleneck in transferring synthetic priors to real scans.
EvObj tackles unsupervised 3D instance segmentation by bridging the domain gap between synthetic and real point clouds, achieving state-of-the-art results on real-world and synthetic datasets.
We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real scans (e.g., ScanNet), particularly due to morphological variations and occlusion artifacts. To address this, EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.