DL3DV-10K/Dataset
News: the 10k dataset is ready for download.
This dataset offers a massive collection of real-world videos (51.2 million frames from 10,510 videos) paired with detailed scene annotations and camera parameters. It serves as a crucial resource for researchers and practitioners in 3D vision, providing the raw material to develop and benchmark deep learning models for tasks like novel view synthesis. Users can access diverse scenes, from indoor to outdoor, with varying reflections, transparency, and lighting conditions.
583 stars.
Use this if you are a 3D vision researcher or developer working on deep learning models for tasks like novel view synthesis (NVS), 3D reconstruction, or learning generalizable 3D representations, and you need a large, diverse, real-world dataset to train and evaluate your models.
Not ideal if you are looking for a simple, out-of-the-box solution for end-user 3D model creation without requiring deep learning research or development.
Stars
583
Forks
15
Language
HTML
License
—
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DL3DV-10K/Dataset"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
opencv/opencv
Open Source Computer Vision Library
pytorch/vision
Datasets, Transforms and Models specific to Computer Vision
kornia/kornia
🐍 Geometric Computer Vision Library for Spatial AI
ermig1979/Simd
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX ...
open-edge-platform/training_extensions
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™