| --- |
| extra_gated_fields: |
| First Name: text |
| Last Name: text |
| Date of birth: date_picker |
| Country: country |
| Affiliation: text |
| Job title: |
| type: select |
| options: |
| - Student |
| - Research Graduate |
| - AI researcher |
| - AI developer/engineer |
| - Reporter |
| - Other |
| geo: ip_location |
| By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox |
| extra_gated_description: >- |
| The information you provide will be collected, stored, processed and shared in |
| accordance with the [Meta Privacy |
| Policy](https://www.facebook.com/privacy/policy/). |
| extra_gated_button_content: Submit |
| extra_gated_heading: "Please be sure to provide your full legal name, date of birth, and full organization name with all corporate identifiers. Avoid the use of acronyms and special characters. Failure to follow these instructions may prevent you from accessing this model and others on Hugging Face. You will not have the ability to edit this form after submission, so please ensure all information is accurate." |
| language: |
| - en |
| pipeline_tag: image-to-image |
| library_name: pytorch |
| tags: |
| - meta-ai |
| - meta-pytorch |
| - surface-normal-estimation |
| - normal-map |
| - hyden |
| license: fair-noncommercial-research-license |
| --- |
| |
| # HyDen MoGe v2 Surface Normal |
|
|
| HyDen is a hybrid dual-path vision encoder for high-resolution monocular |
| geometry that pairs a low-resolution transformer branch for global context |
| with a full-resolution CNN branch for fine detail, delivering |
| state-of-the-art accuracy at a fraction of the inference cost of competing |
| methods. This checkpoint is the HyDen variant of MoGe-v2 for surface normal |
| estimation. |
|
|
| Paper: *Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of |
| High-resolution Images* (ICLR 2026). |
| Code, loader, and inference: **https://github.com/facebookresearch/metadepth** |
|
|
| ## Model details |
|
|
| - Task: monocular surface normal estimation |
| - Output: unit-length per-pixel surface normals |
| - Weights precision: FP32 |
| - Checkpoint: `hyden_mogev2_surface_normal_vitl_fp32_f1076635715.pth` |
| - License: FAIR Noncommercial Research License |
|
|
| ## Usage |
|
|
| Loader, preprocessing, and inference live in the MetaDepth repository: |
| **https://github.com/facebookresearch/metadepth** |
|
|
| Download the checkpoint directly from this page, or via the |
| `huggingface_hub` API: |
|
|
| ```python |
| from huggingface_hub import hf_hub_download |
| |
| ckpt_path = hf_hub_download( |
| repo_id="facebook/hyden-mogev2-surface-normal", |
| filename="hyden_mogev2_surface_normal_vitl_fp32_f1076635715.pth", |
| ) |
| ``` |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{zhang2026hyden, |
| title = {Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of High-resolution Images}, |
| author = {Zaiwei Zhang and Marc Mapeke and Wei Ye and Rakesh Ranjan and JQ Huang}, |
| booktitle = {The Fourteenth International Conference on Learning Representations}, |
| year = {2026}, |
| url = {https://openreview.net/forum?id=2eL6yXLCh8} |
| } |
| ``` |
|
|
| ## Contact |
|
|
| Open an issue on [facebookresearch/metadepth](https://github.com/facebookresearch/metadepth/issues). |
|
|
