Improving neural implicit surfaces geometry with patch warping - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Improving neural implicit surfaces geometry with patch warping

Résumé

Neural implicit surfaces have become an important technique for multi-view 3D reconstruction but their accuracy remains limited. In this paper, we argue that this comes from the difficulty to learn and render high frequency textures with neural networks. We thus propose to add to the standard neural rendering optimization a direct photo-consistency term across the different views. Intuitively, we optimize the implicit geometry so that it warps views on each other in a consistent way. We demonstrate that two elements are key to the success of such an approach: (i) warping entire patches, using the predicted occupancy and normals of the 3D points along each ray, and measuring their similarity with a robust structural similarity (SSIM); (ii) handling visibility and occlusion in such a way that incorrect warps are not given too much importance while encouraging a reconstruction as complete as possible. We evaluate our approach, dubbed NeuralWarp, on the standard DTU and EPFL benchmarks and show it outperforms state of the art unsupervised implicit surfaces reconstructions by over 20% on both datasets. Our code is available at https://github.com/fdarmon/NeuralWarp
Fichier principal
Vignette du fichier
francois_2021.pdf (9.45 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04315790 , version 1 (30-11-2023)

Identifiants

Citer

Francois Darmon, Benedicte Bascle, Jean-Clement Devaux, Pascal Monasse, Mathieu Aubry. Improving neural implicit surfaces geometry with patch warping. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), Jun 2022, La Nouvelle Orléans, LA, United States. pp.6250-6259, ⟨10.1109/CVPR52688.2022.00616⟩. ⟨hal-04315790⟩
32 Consultations
9 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More