Complete 3D Scene Parsing from an RGBD Image

TL;DR

This paper presents a method for complete 3D scene parsing from a single RGBD image, integrating object detection, layout estimation, and occlusion handling to produce detailed 3D models of indoor environments.

Contribution

It introduces a data-driven approach combining CNN-based classification, shape retrieval, and spatial reasoning for comprehensive 3D scene interpretation from RGBD images.

Findings

Achieves detailed 3D scene parsing on NYUd v2 dataset

Effectively handles occlusion and diverse object types

Demonstrates improved accuracy over previous methods

Abstract

One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of orthogonal walls and the extent of objects, modeled with CAD-like 3D shapes. We parse both the visible and occluded portions of the scene and all observable objects, producing a complete 3D parse. Such a scene interpretation is useful for robotics and visual reasoning, but difficult to produce due to the well-known challenge of segmentation, the high degree of occlusion, and the diversity of objects in indoor scenes. We take a data-driven approach, generating sets of potential object regions, matching to regions in training images, and transferring and aligning associated 3D models while encouraging fit to observations and spatial consistency. We use support inference to aid interpretation and propose a retrieval scheme that uses convolutional neural networks (CNNs) to classify regions and retrieve objects with similar shapes. We demonstrate the performance of our method on our newly annotated NYUd v2 dataset with detailed 3D shapes.