#238 · Primary category: Computer Vision
Dataset
News: the 10k dataset is ready for download.
Project last updated:02/10/26
GitHub Stars
665
Forks
17
Contributors
4
License
Other
Why we included this project
DL3DV-10K is a large collection of real-world videos built for 3D vision research, and this repo is the official place to download it. Each scene ships with calibrated camera poses and scene annotations, which is exactly what you need for novel view synthesis, neural radiance fields, or generalizable 3D reconstruction, fields that have long been short on scene-level data at this scale. The project also publishes benchmark training results and a download script, so you can pull a subset and start comparing methods without building your own capture rig. It is a dataset rather than a runnable application, and the non-commercial license makes it a better fit for academic and research use than for commercial product work.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)