---
license: mit
tags:
- depth-estimation
- diffusion
- monocular-depth
- lidar-prompted
- pixel-perfect-depth
- pytorch
---

# LiDAR-Perfect Depth (LPD)

Implementation of *LiDAR-Perfect Depth: Score-Decomposed Diffusion with Kalman-in-the-Loop Denoising for Sparse-Prompted Depth* on top of [Pixel-Perfect Depth](https://github.com/gangweix/pixel-perfect-depth).

## Repos

| Repo | Contents | Size |
|---|---|---|
| `chenming-wu/LiDAR-Perfect-Depth` (this) | code + 6 LPD-DA2 checkpoints + inference vis + extraction helper | 12.5 GB |
| [`chenming-wu/LiDAR-Perfect-Depth-Datasets`](https://huggingface.co/datasets/chenming-wu/LiDAR-Perfect-Depth-Datasets) | extracted eval sets + training-set archives + PPD/DA-V2/RAFT weights | ~991 GB |

## What's in this repo

- `code/` — full LPD codebase. New modules under `ppd/lpd/`; updated configs and adapter loaders.
- `checkpoints/`
  - `e000-s001000.ckpt` … `e004-s005000.ckpt` — per-epoch fine-tuned weights (DA2 backbone, 5K steps)
  - `last.ckpt` — same as e004
  - 2.0 GB each, weights-only
- `inference_vis/` — 8-sample qualitative panels (RGB | GT | PPD | LPD | LPD-variance)
- `extract_archives.sh` — extracts the dataset archives back into the layout the code expects

## Backbone options

PPD (and therefore LPD) support two semantic-prompt backbones — switching is a single config change.

| Backbone | Trainable params | PPD ckpt | Config |
|---|---|---|---|
| **DA2** (Depth-Anything-V2 ViT-L) | 16.3 M | [`gangweix/Pixel-Perfect-Depth/ppd.pth`](https://huggingface.co/gangweix/Pixel-Perfect-Depth/resolve/main/ppd.pth) | `code/ppd/configs/lpd_run5d_10k.yaml` |
| **MoGe2** | 16.3 M | [`chenming-wu/LiDAR-Perfect-Depth-Datasets/pretrained/ppd_moge2/`](https://huggingface.co/datasets/chenming-wu/LiDAR-Perfect-Depth-Datasets/tree/main/pretrained/ppd_moge2) | `code/ppd/configs/lpd_run5d_moge2.yaml` |

The official PPD MoGe2 release reports 20-30 % improvement over DA2 on zero-shot benchmarks; the LPD prompt branch is identical for either backbone.

## Training run summary (DA2 backbone, 5K steps)

```
Backbone:   PPD-DA2 — 820 M, frozen
Trainable:  16 M (sparse-prompt encoder + gate)
Resolution: 1024 × 768
Batch:      18  (~133 GB peak on a single H200)
Steps:      5,000 (5 epochs × 1000 batches)
Mix:        Hypersim 0.5 / UrbanSyn 0.15 / UnrealStereo4K 0.15 / VKITTI2 0.1 / TartanAir 0.1
Init:       gangweix/Pixel-Perfect-Depth ppd.pth

epoch 0 → 4   loss: 0.0186 → 0.0177  (-4.8%)
```

The 5 K steps shown here is a partial-train demo — paper-scale training would push it much further.

For MoGe2 backbone we verified the full forward + backward + checkpointing pipeline works
(`lpd_run5d_moge2.yaml`); training to convergence is left for a multi-GPU run.

## Verification

```bash
cd code/
pip install -r requirements.txt
python -m ppd.lpd.tests.verify_paper      # 30 paper claims, all pass
```

`PAPER_CHECKLIST.md` maps each section of the paper to specific code files/lines.

## Reproducing training

```bash
# Pretrained inputs the code expects
ln -sf <ppd.pth>                          code/checkpoints/ppd.pth                 # DA2
ln -sf <depth_anything_v2_vitl.pth>       code/checkpoints/depth_anything_v2_vitl.pth
# OR for MoGe2:
ln -sf <ppd_moge2.pth>                    code/checkpoints/ppd_moge2.pth
ln -sf <moge2.pt>                         code/checkpoints/moge2.pt

# Hypersim 512² pretrain (DA2)
bash code/train_lpd.sh

# 5-dataset 1024×768 fine-tune
python code/main.py --cfg_file code/ppd/configs/lpd_run5d_10k.yaml      # DA2
# OR
python code/main.py --cfg_file code/ppd/configs/lpd_run5d_moge2.yaml    # MoGe2

# Inference comparison (PPD vs LPD)
python code/experiments/eval_lpd_vs_ppd.py
```

## Datasets — fetching + extracting

Everything is hosted as **archives** in the dataset repo to keep file counts low and upload bandwidth high.

```bash
hf download chenming-wu/LiDAR-Perfect-Depth-Datasets --repo-type dataset \
    --local-dir /mnt/sig/datasets

bash code/extract_archives.sh /mnt/sig/datasets /mnt/sig/datasets/archives
```

Layout after extraction matches what the LPD configs reference (`/mnt/sig/datasets/train/<scene>/...`, `/mnt/sig/datasets/eval_image/...`).

## Citations

- **Pixel-Perfect Depth** — Xu et al., NeurIPS 2025
- **LiDAR-Perfect Depth** — `paper.tex` in this repo