Skip to content
ModelListedExternal
Download

3DCorrEnhance

This repository contains the model introduced in the paper Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning.

Sourcehuggingface.co/qq456cvb/3DCorrEnhance/tree/c73b056f65e3208ffadcb7be5b4287deffb13a2c
KindOtherVersionRevision c73b056

Model source

Kind
Other
File size
15.5–244 MB
Version
vRevision c73b056
Updated
Sep 21, 2026
Downloads
0
Source
Hugging Face

Source description

This repository contains the model introduced in the paper Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning.

Code: https://github.com/qq456cvb/3DCorrEnhance.

Sources

1 source
Hugging FacePrimaryVersion c73b056f65e3208ffadcb7be5b4287deffb13a2c
huggingface.co/qq456cvb/3DCorrEnhance/tree/c73b056f65e3208ffadcb7be5b4287deffb13a2c

Verified Sep 9

Model artifacts

11 artifacts

clip.ckpt

ckpt · 61.3 MB · SHA-256 696734b2a5bb…4851 · Hugging Face

Download

deit.ckpt

ckpt · 61.3 MB · SHA-256 e9badf65dc2b…5c31 · Hugging Face

Download

dinov2_base.ckpt

ckpt · 61.3 MB · SHA-256 6f83bec78ea8…c9b8 · Hugging Face

Download

dinov2_giant.ckpt

ckpt · 244 MB · SHA-256 94a20b01ea7f…3680 · Hugging Face

Download

dinov2_large.ckpt

ckpt · 109 MB · SHA-256 374d4bdee45b…6d3d · Hugging Face

Download

dinov2_reg_base.ckpt

ckpt · 61.3 MB · SHA-256 abd21e97a337…a070 · Hugging Face

Download

dinov2_reg_giant.ckpt

ckpt · 244 MB · SHA-256 a2a2a9b7598b…0da0 · Hugging Face

Download

dinov2_reg_large.ckpt

ckpt · 109 MB · SHA-256 5de902a61d6e…42ec · Hugging Face

Download

dinov2_reg_small.ckpt

ckpt · 15.5 MB · SHA-256 13f772f01be4…2833 · Hugging Face

Download

dinov2_small.ckpt

ckpt · 15.5 MB · SHA-256 34cd1f681269…6503 · Hugging Face

Download

mae.ckpt

ckpt · 61.3 MB · SHA-256 16d0fb309117…6858 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 9huggingface.co/qq456cvb/3DCorrEnhance

--- license: mit pipeline_tag: image-feature-extraction --- This repository contains the model introduced in the paper [Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning](https://huggingface.co/papers/2411.19458). Code: https://github.com/qq456cvb/3DCorrEnhance.

NoteSep 9huggingface.co/qq456cvb/3DCorrEnhance

Source context: 0 downloads · 2 likes · Pipeline image-feature-extraction · Repo qq456cvb/3DCorrEnhance