Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911320438210560 |
|---|---|
| author | Nazarczuk, Michal Tanay, Thomas Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo |
| author_facet | Nazarczuk, Michal Tanay, Thomas Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13639 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All Nazarczuk, Michal Tanay, Thomas Moreau, Arthur Zhang, Zhensong Pérez-Pellitero, Eduardo Computer Vision and Pattern Recognition 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. |
| title | Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.13639 |