Aller au contenu
ModelPrésentéExterne
Télécharger

SeeGroup

we propose SeeGroup, a multi-layer depth estimation method that allows the model itself to adaptively assign surfaces to depth maps. We formulate per-pixel multi-layer depth as a point process, treating depth layers...

TypeOtherVersionVersion 1CClasse

Source du modèle

Type
Other
Taille du fichier
3,97 GB
Version
vVersion 1
Mis à jour
10 oct. 2026
Source
Hugging Face

Description de la source

[CVPR 2026] SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping

we propose SeeGroup, a multi-layer depth estimation method that allows the model itself to adaptively assign surfaces to depth maps. We formulate per-pixel multi-layer depth as a point process, treating depth layers as unordered events along each camera ray. This induces a permutation-invariant likelihood over the observed depth layers, yielding a loss that naturally supports arbitrary layer groupings. Experiments demonstrate that our method significantly advances the state of the art of multi-layer depth estimation, improving quadruplet relative depth accuracy on LayeredDepth benchmark from 61.34% to 70.09%. Code is available at https://github.com/princeton-vl/SeeGroup.

Sources

1 source
Hugging FacePrincipalVersion 43d982a03ee786596f11a8358850c3b93e517e9d
huggingface.co/Hermera/SeeGroup/tree/43d982a03ee786596f11a8358850c3b93e517e9d

Vérifié 10 oct.

Artefacts du modèle

1 artefact

seegroup.pth

pth · 3,97 GB · SHA-256 c21ccdd1595f…9c77 · Hugging Face

Download file

Extraits de sources

2 extraits

--- license: bsd-3-clause pipeline_tag: depth-estimation --- # [CVPR 2026] SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping we propose SeeGroup, a multi-layer depth estimation method that allows the model itself to adaptively assign surfaces to depth maps. We formulate per-pixel multi-layer depth as a point process, treating depth layers as unordered events along each camera ray. This induces a permutation-invariant likelihood over the observed depth layers, yielding a loss that naturally supports arbitrary layer groupings. Experiments demonstrate that our method significantly advances the state of the art of multi-layer depth estimation, improving quadruplet relative depth accuracy on LayeredDepth benchmark from 61.34% to 70.09%. Code is available at https://github.com/princeton-vl/SeeGroup.

Source context: 0 downloads · 0 likes · Pipeline depth-estimation · Repo Hermera/SeeGroup