Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
This dataset addresses the need for comprehensive benchmarks in novel view synthesis for researchers in 3D vision and computer graphics, though it is incremental as it builds on existing datasets by offering richer annotations and varied setups.
The authors introduced a new dataset for novel view synthesis, generated from a high-quality animated film with detailed textures, lighting, and motion, providing RGB images and multiple complementary modalities like depth and optical flow. The dataset includes three benchmarking scenarios (dense multi-view, sparse camera, and monocular video) to enable diverse experimentation in 4D scene reconstruction and view generation.
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.