The DL3DV-10K is a large-scale multi-view scene dataset designed to address challenges in neural view synthesis. The research team evaluated existing methods using DL3DV-10K and proposed the performance benchmark DL3DV-140. Results indicate that pre-training IBRNet with DL3DV-10K can significantly enhance the performance of current state-of-the-art methods. The study underscores the importance of large-scale real-world scene datasets in advancing the development of learning-based general NeRF methods.