Downloads · 30 days
0
LiteAnyStereoV2
tomtomtommi/LiteAnyStereoV2
LiteAnyStereoV2 is a depth estimation model from tomtomtommi. Use it for the depth estimation task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
- GitHub: https://github.com/TomTomTommi/LiteAnyStereo - LAS1 Paper: https://arxiv.org/abs/2511.16555 - LAS1 Project Page: https://tomtomtommi.github.io/LiteAnyStereo/ - LAS2 Paper: https://arxiv.org/abs/2606.24457 -…
Access
Public
Updated Jun 26, 2026
Repo size
222 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pth222 MB · 100%
At a glance
- Task
- Depth Estimation
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026
- SHA
- 17788d91
Model card
From the Hugging Face model README
Links
- GitHub: https://github.com/TomTomTommi/LiteAnyStereo
- LAS1 Paper: https://arxiv.org/abs/2511.16555
- LAS1 Project Page: https://tomtomtommi.github.io/LiteAnyStereo/
- LAS2 Paper: https://arxiv.org/abs/2606.24457
- LAS2 Project Page: https://tomtomtommi.github.io/LiteAnyStereoV2/
Lite Any Stereo V2
This repository provides pretrained checkpoints for Lite Any Stereo V2 (LAS2), an efficient stereo matching model series designed for practical inference latency and strong zero-shot generalization.
Checkpoints
| Model | Checkpoint |
|---|---|
| LAS2-S | LAS2_S.pth |
| LAS2-M | LAS2_M.pth |
| LAS2-L | LAS2_L.pth |
| LAS2-H | LAS2_H.pth |
Usage
The checkpoints can be downloaded programmatically with huggingface_hub:
from huggingface_hub import hf_hub_download
import torch
ckpt_path = hf_hub_download(
repo_id="tomtomtommi/LiteAnyStereoV2",
filename="LAS2_M.pth"
)
checkpoint = torch.load(ckpt_path, map_location="cpu")
- Task
- Depth Estimation
- Library
- pytorch
- License
- mit
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026