DF-NeRf: A geometrically consistent 3D reconstruction method for blurry images with decoupled and spatial fusion

Puntos clave

• This method enhances 3D reconstruction accuracy for images affected by blurriness, preserving geometrical consistency.
• The proposed approach decouples and spatially fuses image data for better clarity and detail in 3D models.
• Analysis focuses on a detailed methodology to reconstruct 3D representations while addressing image blurriness.
• The findings support advancements in 3D modeling, being particularly relevant for applications in augmented reality.