Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nazarczuk, Michal, Tanay, Thomas, Moreau, Arthur, Zhang, Zhensong, Pérez-Pellitero, Eduardo
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