Hugging Face's logo

siyan824
/
reloc3r-224

Image-to-3D
Safetensors
camera pose estimation
Model card Files Community
1

[CVPR 2025] Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Paper: https://huggingface.co/papers/2412.08376

Code: https://github.com/ffrivera0/reloc3r

Downloads last month
128
Safetensors
Model size
427M params
Tensor type
F32
·
Inference Providers NEW
Image-to-3D
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support