A learning based depth estimation framework for 4D densely and sparsely sampled light fields - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A learning based depth estimation framework for 4D densely and sparsely sampled light fields

Résumé

This paper proposes a learning based solution to disparity (depth) estimation for either densely or sparsely sampled light fields. Disparity between stereo pairs among a sparse subset of anchor views is first estimated by a fine-tuned FlowNet 2.0 network adapted to disparity prediction task. These coarse estimates are fused by exploiting the photo-consistency warping error, and refined by a Multi-view Stereo Refinement Network (MSRNet). The propagation of disparity from anchor viewpoints towards other viewpoints is performed by an occlusion-aware soft 3D reconstruction method. The experiments show that, both for dense and sparse light fields, our algorithm outperforms significantly the state-of-the-art algorithms, especially for subpixel accuracy.
Fichier principal
Vignette du fichier
icassp2019-depth.pdf (4.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02116375 , version 1 (30-04-2019)

Identifiants

Citer

Xiaoran Jiang, Jinglei Shi, Christine Guillemot. A learning based depth estimation framework for 4D densely and sparsely sampled light fields. ICASSP 2019 - IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2019, Brighton, United Kingdom. pp.2257-2261, ⟨10.1109/ICASSP.2019.8683773⟩. ⟨hal-02116375⟩
42 Consultations
184 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More