Complete 3D Scene Parsing from an RGBD Image
This addresses the challenge of scene interpretation for robotics and visual reasoning, but it is incremental as it builds on existing methods for segmentation and object retrieval.
The paper tackles the problem of parsing complete 3D scenes, including visible and occluded parts, from a single RGBD image, using a data-driven approach that matches regions to training data and aligns 3D models, achieving results demonstrated on a newly annotated NYUd v2 dataset.
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.