Charge：一个统一绑定所有任务的全新视角合成综合基准与数据集
Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
该数据集同时提供深度、表面法线、分割与光流等多模态真值，并设置稠密多视角、稀疏相机与单目视频三种基准场景，可直接用于评测4D重建与新视角合成方法在不同数据稀疏度下的鲁棒性，也为多模态监督训练提供了现成的配对数据。
原文依据 a dense multi-view camera setup, a sparse camera arrangement, and monocular video sequences
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出了一个新视角合成数据集，其数据由一部高质量动画电影生成，画面具有惊人的真实感与丰富的细节。该数据集包含多种动态场景，并配有细致的纹理、光照与运动信息，非常适合用于训练和评测前沿的4D场景重建与新视角生成模型。除高保真RGB图像外，我们还提供多种互补模态，包括深度、表面法线、物体分割与光流，从而支持对场景几何与运动的更深入理解。该数据集被组织为三个不同的基准场景：稠密多视角相机设置、稀疏相机布局以及单目视频序列，从而能够在不同数据稀疏程度下开展广泛的实验与比较。凭借视觉丰富性、高质量标注与多样化实验设置的结合，该数据集为推动视角合成与3D视觉的发展提供了独特的资源。
英文原文摘要 1045 字符
This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety of dynamic scenes, complete with detailed textures, lighting, and motion, making it ideal for training and evaluating cutting-edge 4D scene reconstruction and novel view generation models. In addition to high-fidelity RGB images, we provide multiple complementary modalities, including depth, surface normals, object segmentation and optical flow, enabling a deeper understanding of scene geometry and motion. The dataset is organised into three distinct benchmarking scenarios: a dense multi-view camera setup, a sparse camera arrangement, and monocular video sequences, enabling a wide range of experimentation and comparison across varying levels of data sparsity. With its combination of visual richness, high-quality annotations, and diverse experimental setups, this dataset offers a unique resource for pushing the boundaries of view synthesis and 3D vision.