TopoPT

Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation

**** · GitHub · Paper

---

Model Overview

TopoPT is a family of lightweight 3D point cloud segmentation models obtained by compressing LitePT-S through a compact student architecture (TrimPT) trained with Stage-wise Relational Feature Distillation (SRFD).

TrimPT reduces LitePT-S's channel widths from (36, 72, 144, 252, 504) to (36, 54, 108, 180, 360) and cuts stage-3 attention depth from 6 to 4 blocks, preserving the full 1024-token attention window. This yields 5.84 M parameters and 12.95 GFLOPs — 2.18× fewer parameters and 1.96× fewer FLOPs than LitePT-S.

SRFD is a training-only objective applied at the compressed attention stages (stages 3–4). It matches pairwise cosine-similarity matrices between teacher (frozen LitePT-S) and student (TrimPT) features, explicitly regularizing their local affinity structure. Stage-specific linear projectors align teacher and student channel dimensions before computing both a pointwise cosine loss (L_pw) and a relational Frobenius loss (L_rel). After training, the teacher and all projectors are discarded — TopoPT has the same deployed architecture, checkpoint size, FLOPs, and latency as TrimPT.

On ScanNet semantic segmentation, TopoPT achieves 76.6% mIoU at 5.84 M parameters — matching the official LitePT-S result (76.5%) with substantially fewer resources.

---

Available Checkpoints

All checkpoints follow the naming convention {dataset}-{task}-{model}-{epochs}.
lw-c = TrimPT (no distillation) · lw-c-kd = TopoPT (with SRFD)

Semantic Segmentation

Instance Segmentation

Ablation Checkpoints (ScanNet, 100 epochs)

These correspond to the compression ablation study (Table 2 in the paper).

---

Inference Efficiency

Profiled on NVIDIA RTX 3090 (batch size 1, 300 forward passes). Since the teacher and projectors are discarded after training, TopoPT and TrimPT have identical inference cost.

---

How to Use

Please refer to the GitHub repository for full setup, training, and evaluation instructions. The codebase follows the same interface as LitePT and Pointcept.

Quick start — loading a TopoPT checkpoint for inference:

# Install and set up environment following the GitHub README, then:
export PYTHONPATH=./
python tools/test.py \
    --config-file configs/scannet/semseg-lw-c-kd-100epoch.py \
    --num-gpus 4 \
    --options save_path=exp/topopt_scannet \
              weight=/path/to/model_best.pth

---

Architecture Details

Stages 1–2 use sparse convolution; stages 3–4 use windowed multi-head self-attention with PointROPE positional encoding (same as LitePT). SRFD distillation is applied at stages 3–4 during training only.

---

Citation

@inproceedings{topopt2026,
    title={{Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation}},
    author={Anonymous},
    booktitle={...},
    year={2026}
}

@inproceedings{yuelitept2026,
    title={{LitePT: Lighter Yet Stronger Point Transformer}},
    author={Yue, Yuanwen and Robert, Damien and Wang, Jianyuan and Hong, Sunghwan and Wegner, Jan Dirk and Rupprecht, Christian and Schindler, Konrad},
    booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2026}
}