Top-Down Beats Bottom-Up in 3D Instance Segmentation

6 Feb 2023  ·  Maksim Kolodiazhnyi, Danila Rukhovich, Anna Vorontsova, Anton Konushin ·

Most 3D instance segmentation methods exploit a bottom-up strategy, typically including resource-exhaustive post-processing. For point grouping, bottom-up methods rely on prior assumptions about the objects in the form of hyperparameters, which are domain-specific and need to be carefully tuned. On the contrary, we address 3D instance segmentation with a TD3D: top-down, fully data-driven, simple approach trained in an end-to-end manner. With its straightforward fully-convolutional pipeline, it performs surprisingly well on the standard benchmarks: ScanNet v2, its extension ScanNet200, and S3DIS. Besides, our method is much faster on inference than the current state-of-the-art grouping-based approaches. Code is available at .

PDF Abstract

Results from the Paper

Ranked #3 on 3D Instance Segmentation on S3DIS (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Instance Segmentation S3DIS TD3D AP@50 70.4 # 3
mAP 58.1 # 3
3D Instance Segmentation ScanNet(v2) TD3D mAP 48.9 # 7
mAP @ 50 75.1 # 5
mAP@25 87.5 # 1


No methods listed for this paper. Add relevant methods here