---
license: mit
tags:
- photometric-stereo
- normal-estimation
- lino-unips
- lvc
library_name: pytorch
---

# LiNo-UniPS + LVC checkpoints

Checkpoints for bachelor thesis: **Lighting Variation Confidence (LVC) module on LiNo-UniPS** — Đoàn Anh Vũ, HUST SOICT.

## Variants

| Folder | Variant | Description |
|---|---|---|
| `bl_real_*` | `baseline` | Original LiNo-UniPS (no LVC) |
| `fl_real_*` | `lvc_full` | LiNo-UniPS + LVC full (loss weighting + feature scaling, **proposed method**) |
| `ll_real_*` | `lvc_loss` | LVC loss weighting only (ablation) |
| `lf_real_*` | `lvc_feat` | LVC feature scaling only (ablation) |

Filename convention: `{variant_short}_{mode}_{DDMMYYYY}_{HHMMSS}_e{epoch}_v{val_loss}.ckpt`

- `variant_short`: `bl` / `fl` / `ll` / `lf`
- `mode`: `smoke` (test) / `real` (production)

## Training setup

- Dataset: HDLong + (PolarPS future), hosted at [HUST-CVLab-PS/UniPS](https://huggingface.co/datasets/HUST-CVLab-PS/UniPS)
- Hardware: NVIDIA RTX 6000 Ada (Vast.ai)
- Optimizer: AdamW(lr=1e-4, wd=0.05), StepLR(step=10, gamma=0.8)
- Precision: bf16-mixed
- K input images: 6 (HDLong)
- Hyperparams khác xem wandb run config

## Acknowledgments

Base architecture & weights: [LiNo-UniPS](https://github.com/houyuanchen111/LINO_UniPS) (MIT License) by H. Li, H. Chen et al.
- Paper: [arXiv 2506.18882](https://arxiv.org/abs/2506.18882)
- Original model card: [houyuanchen/lino](https://huggingface.co/houyuanchen/lino)

## License

MIT — same as upstream LiNo-UniPS.