4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding

6 Dec 2021  ·  Yujin Chen, Matthias Nießner, Angela Dai ·

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness, and thus propose to imbue learned 3D representations with such dynamic understanding, that can then be effectively transferred to improved performance in downstream 3D semantic scene understanding tasks. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments, and employ contrastive learning under 3D-4D constraints that encode 4D invariances into the learned 3D representations. Experiments demonstrate that our unsupervised representation learning results in improvement in downstream 3D semantic segmentation, object detection, and instance segmentation tasks, and moreover, notably improves performance in data-scarce scenarios.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Instance Segmentation ScanNet(v2) 4DContrast mAP @ 50 57.6 # 19

Methods