DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
Abstract
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/.
Community
European-style buildings, pastoral scenery
Fire. I'm assuming it has consistent camera angles? Thanks. so many HQ datasets being released.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting (2023)
- ZeroRF: Fast Sparse View 360{\deg} Reconstruction with Zero Pretraining (2023)
- MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis (2023)
- CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering (2023)
- DGNR: Density-Guided Neural Point Rendering of Large Driving Scenes (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
Check the GitHub repo for data download:
https://github.com/DL3DV-10K/Dataset
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper