Depth Estimation
Diffusers
Safetensors
video-depth-estimation
panoramic-video
equirectangular
pvdepth
Instructions to use Soon122/PVDepth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Soon122/PVDepth with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Soon122/PVDepth", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
metadata
license: other
library_name: diffusers
pipeline_tag: depth-estimation
base_model: tencent/DepthCrafter
datasets:
- Soon122/PanoCARLA
tags:
- depth-estimation
- video-depth-estimation
- panoramic-video
- equirectangular
- diffusers
- pvdepth
PVDepth
This repository provides the UNet checkpoint for PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation. It estimates temporally consistent relative inverse depth from equirectangular images and videos.
Usage
GPU_ID=0 bash run_infer_any.sh \
<input_path> \
Soon122/PVDepth \
./outputs
See the PVDepth repository for installation and usage. The training dataset is available at PanoCARLA.
Citation
@inproceedings{song2026pvdepth,
author = {Song, Chuanxin and Peng, Peixi},
title = {PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation},
booktitle = {ICML},
year = {2026}
}
License
This checkpoint is subject to the upstream licenses of DepthCrafter and Stable Video Diffusion. See the PVDepth repository for details.