DeepAI AI Chat
Log In Sign Up

Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans

by   Ainaz Eftekhar, et al.

This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world. Changing the sampling parameters allows one to "steer" the generated datasets to emphasize specific information. In addition to enabling interesting lines of research, we show the tooling and generated data suffice to train robust vision models. Common architectures trained on a generated starter dataset reached state-of-the-art performance on multiple common vision tasks and benchmarks, despite having seen no benchmark or non-pipeline data. The depth estimation network outperforms MiDaS and the surface normal estimation network is the first to achieve human-level performance for in-the-wild surface normal estimation – at least according to one metric on the OASIS benchmark. The Dockerized pipeline with CLI, the (mostly python) code, PyTorch dataloaders for the generated data, the generated starter dataset, download scripts and other utilities are available through our project website,


page 1

page 3

page 4

page 5

page 6

page 7

page 8


Surface Normals in the Wild

We study the problem of single-image depth estimation for images in the ...

Zap: Making Predictions Based on Online User Behavior

This paper introduces Zap, a generic machine learning pipeline for makin...

HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures

We present HoliCity, a city-scale 3D dataset with rich structural inform...

Multi-Task Self-Training for Learning General Representations

Despite the fast progress in training specialized models for various tas...

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture

In this paper we address three different computer vision tasks using a s...

3D endoscopic depth estimation using 3D surface-aware constraints

Robotic-assisted surgery allows surgeons to conduct precise surgical ope...

Instance-Level Task Parameters: A Robust Multi-task Weighting Framework

Recent works have shown that deep neural networks benefit from multi-tas...