SHRED: 3D Shape Region Decomposition with Learned Local Operations
This addresses the need for accurate and flexible part segmentation in 3D shapes, with applications in tasks like zero-shot instance segmentation, though it appears incremental as it builds on existing segmentation methods and datasets like PartNet.
The paper tackles the problem of 3D shape region decomposition by introducing SHRED, a method that uses learned local operations to segment point clouds into fine-grained part instances, producing segmentations that better respect ground-truth annotations compared to baselines at any desired granularity.
We present SHRED, a method for 3D SHape REgion Decomposition. SHRED takes a 3D point cloud as input and uses learned local operations to produce a segmentation that approximates fine-grained part instances. We endow SHRED with three decomposition operations: splitting regions, fixing the boundaries between regions, and merging regions together. Modules are trained independently and locally, allowing SHRED to generate high-quality segmentations for categories not seen during training. We train and evaluate SHRED with fine-grained segmentations from PartNet; using its merge-threshold hyperparameter, we show that SHRED produces segmentations that better respect ground-truth annotations compared with baseline methods, at any desired decomposition granularity. Finally, we demonstrate that SHRED is useful for downstream applications, out-performing all baselines on zero-shot fine-grained part instance segmentation and few-shot fine-grained semantic segmentation when combined with methods that learn to label shape regions.