PulseAugur
实时 10:57:57
English(EN) DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

新的DF3DV-1K数据集推动无干扰新视角合成研究

研究人员推出了DF3DV-1K,一个旨在推动无干扰新视角合成研究的大规模数据集。该数据集包含1000多个场景,每个场景都有干净和杂乱的图像集,总计近90,000张由消费级相机拍摄的图像。它包括128种干扰物和161个场景主题,其中一个特定子集DF3DV-41被精心策划用于评估方法的鲁棒性。该数据集已被用于对现有的辐射场方法和3D高斯溅射进行基准测试,并用于微调基于扩散的增强器,在渲染质量方面显示出显著的改进。 AI

影响 促进开发超越场景特定方法、更鲁棒和更具泛化性的新视角合成技术。

排序理由 该集群描述了一个用于特定计算机视觉任务的新学术数据集和基准测试,发布在arXiv上。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的DF3DV-1K数据集推动无干扰新视角合成研究

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi, Hao-Ping Wang, Charlie Li-Ting Tsai, Yu-Cheng Chang, Yu-Lun Liu, Thomas Do, Chin-Teng Lin ·

    DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

    arXiv:2604.13416v2 Announce Type: replace-cross Abstract: Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond …

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

    A large-scale real-world dataset called DF3DV-1K is introduced to address the lack of clean and cluttered image sets for distractor-free radiance field research, containing 1,048 scenes with 89,924 images across 128 distractor types and 161 scene themes, along with a curated subs…