Dynamic Convolution for 3D Point Cloud Instance Segmentation
arXiv:2107.08392
Abstract
We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches, including a dependence on hyper-parameter tuning and heuristic post-processing pipelines to compensate for the inevitable variability in object sizes, even within a single scene. The representation capability of the network is greatly improved by gathering homogeneous points that have identical semantic categories and close votes for the geometric centroids. Instances are then decoded via several simple convolution layers, where the parameters are generated conditioned on the input. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance. A light-weight transformer, built on the bottleneck layer, allows the model to capture long-range dependencies, with limited computational overhead. The result is a simple, efficient, and robust approach that yields strong performance on various datasets: ScanNetV2, S3DIS, and PartNet. The consistent improvements on both voxel- and point-based architectures imply the effectiveness of the proposed method. Code is available at: https://git.io/DyCo3D
Accepted to IEEE Trans. Pattern Analysis and Machine Intelligence. Extended version of arXiv:2011.13328
References in corpus (8)
- A Simple Framework for Contrastive Learning of Visual Representations
- Improved Baselines with Momentum Contrastive Learning
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Semantic Instance Segmentation with a Discriminative Loss Function
- Deep Continuous Fusion for Multi-Sensor 3D Object Detection
- Pay Less Attention with Lightweight and Dynamic Convolutions
- MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
- PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection