Checkpoints for the submission "relabelling voxel indices"
Weights of the models we trained for the paper, to be read with the code release (an overlay
on Pointcept v1.7.0). Every model here was trained
from scratch with Pointcept's unmodified model code; no third-party weights are included.
Layout: exp/<dataset>/<config>/model/model_best.pth plus the run's train.log. The directory
name is the Pointcept configuration that trained it; a second seed ends in -seed1. Each file
holds the model state_dict (plus epoch and best_metric_value); optimizer state is removed.
SHA256SUMS lists the hashes. The published LitePT-S checkpoints the paper also reads are not
copied here: they are on prs-eth/LitePT.
| dataset | checkpoints |
|---|---|
| ScanNet v2 | semseg-litept-v1m1-0-small, semseg-litept-v1m1-0b-small-scaleaug, semseg-litept-v1m1-0-small-train3tau, semseg-litept-v1m2-0-small (+ -seed1), semseg-pt-v3m1-0-base, semseg-spunet-v1m1-0-base, semseg-pt-v2m2-0-base, insseg-pointgroup-v1m1-0-spunet-base |
| nuScenes | semseg-litept-v1m1-0-small (+ -seed1), semseg-litept-v1m1-0b-small-scaleaug (+ -seed1), semseg-litept-v1m2-0-small, semseg-litept-v1m2-0b-small-scaleaug, semseg-pt-v3m1-0-base, semseg-spunet-v1m1-0-base |
Licence and data terms
These weights are released for non-commercial research only, under CC BY-NC-SA 4.0, because of the data they were trained on:
- nuScenes is provided by Motional under CC BY-NC-SA 4.0 and the nuScenes Terms of Use. The nuScenes checkpoints are shared under the same licence. This release is not endorsed by Motional. Caesar et al., nuScenes: A multimodal dataset for autonomous driving, CVPR 2020.
- ScanNet may be used for non-commercial research and educational purposes only, under the ScanNet Terms of Use. No ScanNet data is included here. Dai et al., ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes, CVPR 2017.
The training and model code (Pointcept, LitePT) is MIT-licensed and is not included here.