SCRREAM : SCan, Register, REnder And Map:A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark

TL;DR

SCRREAM is a comprehensive framework for annotating dense 3D indoor scene meshes and camera poses, enabling accurate evaluation of dense geometry tasks with high-quality ground truth data.

Contribution

The paper introduces SCRREAM, a novel annotation framework that produces accurate dense meshes and camera registration, improving ground truth quality for indoor 3D scene analysis.

Findings

Enables evaluation of dense geometry tasks with accurate ground truth.

Supports multiple dataset variants for diverse indoor scene applications.

Provides new benchmarks for indoor reconstruction and SLAM.

Abstract

Traditionally, 3d indoor datasets have generally prioritized scale over ground-truth accuracy in order to obtain improved generalization. However, using these datasets to evaluate dense geometry tasks, such as depth rendering, can be problematic as the meshes of the dataset are often incomplete and may produce wrong ground truth to evaluate the details. In this paper, we propose SCRREAM, a dataset annotation framework that allows annotation of fully dense meshes of objects in the scene and registers camera poses on the real image sequence, which can produce accurate ground truth for both sparse 3D as well as dense 3D tasks. We show the details of the dataset annotation pipeline and showcase four possible variants of datasets that can be obtained from our framework with example scenes, such as indoor reconstruction and SLAM, scene editing & object removal, human reconstruction and 6d pose estimation. Recent pipelines for indoor reconstruction and SLAM serve as new benchmarks. In contrast to previous indoor dataset, our design allows to evaluate dense geometry tasks on eleven sample scenes against accurately rendered ground truth depth maps.