Aller au contenu
ModelPrésentéExterne
Browse files

PRM

Model card for PRM: Photometric Stereo based Large Reconstruction Model.

TypeOtherVersionRevision e9a40a1UnratedClasse

Source du modèle

Type
Other
Taille du fichier
1,41–4,29 GB
Version
vRevision e9a40a1
Mis à jour
4 nov. 2026
Téléchargements
2,2 k
Source
Hugging Face

Description de la source

PRM

Model card for PRM: Photometric Stereo based Large Reconstruction Model.

Code: https://github.com/g3956/PRM

Arxiv: http://arxiv.org/abs/2412.07371

Gradio demo: https://huggingface.co/spaces/LTT/PRM

We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details. Unlike previous large reconstruction models that prepare images under fixed and simple lighting as both input and supervision, PRM renders photometric stereo images by varying materials and lighting for the purposes, which not only improves the precise local details by providing rich photometric cues but also increases the model’s robustness to variations in the appearance of input images. To offer enhanced flexibility of images rendering, we incorporate a real-time rendering method and mesh rasterization for online images rendering. Moreover, in employing an explicit mesh as our 3D representation, PRM ensures the application of differentiable PBR, which supports the utilization of multiple photometric supervisions and better models the specular color for high-quality geometry optimization. Our PRM leverages photometric stereo images to achieve high-quality reconstructions with fine-grained local details, even amidst sophisticated image appearances. Extensive experiments demonstrate that PRM significantly outperforms other models.

Sources

1 source
Hugging FacePrincipalVersion e9a40a1e6dce3c247a36347c6f90b2b859ab726e
huggingface.co/LTT/PRM/tree/e9a40a1e6dce3c247a36347c6f90b2b859ab726e

Vérifié 4 nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

3 artefacts

diffusion_pytorch_model.bin

bin · 1,61 GB · SHA-256 9d78d78421d1…a3c4 · Hugging Face

Download file

final_ckpt.ckpt

ckpt · 4,29 GB · SHA-256 b33b7f8489ac…7c57 · Hugging Face

Download file

PRM_nerf_large.ckpt

ckpt · 1,41 GB · SHA-256 530a344ea9b8…2fb9 · Hugging Face

Download file

Extraits de sources

3 extraits

--- license: apache-2.0 tags: - image-to-3d --- # PRM Model card for *PRM: Photometric Stereo based Large Reconstruction Model*. Code: https://github.com/g3956/PRM Arxiv: http://arxiv.org/abs/2412.07371 Gradio demo: https://huggingface.co/spaces/LTT/PRM We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details. Unlike previous large reconstruction models that prepare images under fixed and simple lighting as both input and supervision, PRM renders photometric stereo images by varying materials and lighting for the purposes, which not only improves the precise local details by providing rich photometric cues but also increases the model’s robustness to variations in the appearance of input images. To offer enhanced flexibility of images rendering, we incorporate a real-time rendering method and mesh rasterization for online images rendering. Moreover, in employing an explicit mesh as our 3D representation, PRM ensures the application of differentiable PBR, which supports the utilization of multiple photometric supervisions and better models the specular color for high-quality geometry optimization. Our PRM leverages photometric stereo images to achieve high-quality reconstructions with fine-grained local details, even amidst sophisticated image appearances. Extensive experiments demonstrate that PRM significantly outperforms other models.

Source context: 2195 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo LTT/PRM

Source context: 45 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo LTT/PRM