Novel View Synthesis

SPARF is a large-scale ShapeNet-based synthetic dataset for novel view synthesis consisting of ~17 million images rendered from nearly 40,000 shapes at high resolution (400×400 pixels). Source: SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images Image Source: https://github.com/ajhamdi/sparf_pytorch

A real-world low-light camera motion blur dataset for evaluating deblurring radiance fields methods. Five indoor scenes using a machine vision camera, each providing 20-40 multi-view blurry images, including 3-5 images for novel-view synthesis evaluation.

The first large-scale dataset for training and evaluating novel-view synthesis from blurred images. The dataset comprises a train set and a test set for each type of blur: camera motion blur and defocus blur. The train set includes 65 scenes, each containing 29 pairs of synthetically blurred images and their corresponding sharp images, captured from different viewpoints. The test set includes 10 scenes, each with 29 blurred-sharp image pairs and five additional sharp images from different viewpoints for evaluating novel-view synthesis quality.

LLNeRF Dataset is a real-world dataset as a benchmark for model learning and evaluation. To obtain real low-illumination images with real noise distributions, photos are taken at nighttime outdoor scenes or low-light indoor scenes containing diverse objects. Since the ISP operations are device dependent and the noise distributions across devices are also different, the data is collected using a mobile phone camera and a DSLR camera to enrich the diversity of the dataset.

Replay is a collection of multi-view, multi-modal videos of humans interacting socially. Each scene is filmed in high production quality, from different viewpoints with several static cameras, as well as wearable action cameras, and recorded with a large array of microphones at different positions in the room. The full Replay dataset consists of 68 scenes of social interactions between people, such as playing boarding games, exercising, or unwrapping presents. Each scene is about 5 minutes long and filmed with 12 cameras, static and dynamic. Audio is captured separately by 12 binaural microphones and additional near-range microphones for each actor and for each egocentric video. All sensors are temporally synchronized, undistorted, geometrically calibrated, and color calibrated.

This synthetic event dataset is used in Robust e-NeRF to study the collective effect of camera speed profile, contrast threshold variation and refractory period on the quality of NeRF reconstruction from a moving event camera. It is simulated using an improved version of ESIM with three different camera configurations of increasing difficulty levels (i.e. easy, medium and hard) on seven Realistic Synthetic $360^{\circ}$ scenes (adopted in the synthetic experiments of NeRF), resulting in a total of 21 sequence recordings. Please refer to the Robust e-NeRF paper for more details. The dataset allows for a retrospective comparison between event-based and image-based NeRF reconstruction methods, as the event sequences were simulated under highly similar conditions as the NeRF synthetic dataset. In particular, we adopt the same camera intrinsics and camera distance to the object at the origin. Furthermore, the event camera travels in a hemi-/spherical spiral motion about the object, thereby having a similar camera pose distribution for training. Apart from that, we also use the same test camera poses/views. Nonetheless, this new synthetic event dataset is not only specific to NeRF reconstruction, but also suitable for novel view synthesis, 3D reconstruction, localization and SLAM in general.

Synthetic dataset comprising three different environments for multi-camera dynamic novel view synthesis for soccer. This dataset is made compatible for Nerfstudio, and includes data parsers with various settings to reproduce the settings of our paper "Dynamic NeRFs for Soccer Scenes" and more. The data consists of 3 synthetic scenes built using Blender. Each scene contains from 20 to 30 synchronized and calibrated cameras that capture a 4-second long scene at 25 FPS. For each scene, the downloadable data consists of images and corresponding poses. These are ready to use either with our code, either with Nerfstudio using the slightly different data parsers available in this folder. Please contact the corresponding author (sacha.lewin@uliege.be) if you need the Blender scenes.

Dataset of paired thermal and RGB images comprising ten diverse scenes—six indoor and four outdoor scenes— for 3D scene reconstruction and novel view synthesis (e.g. with NeRF).

bbb

HuSc3D is a novel dataset specifically designed for rigorous benchmarking of 3D reconstruction models under realistic acquisition challenges. Our dataset uniquely features six highly detailed, fully white sculptures characterized by intricate perforations and minimal textural and color variation. Furthermore, the number of images per scene varies significantly, introducing the additional challenge of limited training data for some instances alongside scenes with a standard number of views.