« Retourner aux résultats de recherche

• Citer

∂DIBR: Differentiable Depth Image-based Rendering for Fast Novel View Synthesis

par Losfeld, Armand ;Dury, Sarah ;Lafruit, Gauthier ;Teratani, Mehrdad ;Bonatto, Daniele
Référence The 19th European Conference on Computer Vision -- ECCV 2026(19: September 8 – 12th, 2026: Malmö, Sweden), European Conference on Computer Vision
Publication Publié, 2026-06-01

Publication dans des actes

• Détails
• Contenu

Résumé :

Modern Novel View Synthesis (NVS), such as 3D Gaussian Splatting (3DGS), introduces scene representations based on new parametrized primitives. These primitives are optimized through inverse-rendering optimization from color gradients, possibly with a depth prior. However, they fail to preserve geometric consistency and connectivity of the scene during the training phase. Furthermore, standard computer graphics (CG) pipelines do not easily handle these new primitives, thereby limiting rendering performance and integration into consumer applications. We propose a differentiable framework for Depth Image‑Based Rendering (DIBR) using triangle primitives. Our method integrates seamlessly into traditional CG pipelines while remaining fully optimizable within modern NVS frameworks. Moreover, our primitives ensure geometric consistency and connectivity. Colors and depths are jointly optimized following a coarse-to-fine strategy. We compare our renderer to 3DGS, 2DGS, and Triangle Splatting across two forward‑facing datasets. Although our approach yields slightly lower NVS quality (up to -3 dB), it achieves a 2x speed‑up in rendering time (277 FPS) on a consumer-grade GPU, demonstrating its suitability for real‑time or resource‑constrained applications.