Learn More
In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing single-view 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter(More)
In this paper we show that a geometric representation of an object occurring in indoor scenes, along with rich scene structure can be used to produce a detector for that object in a single image. Using perspective cues from the global scene geometry, we first develop a 3D based object detector. This detector is competitive with an image based detector built(More)
We propose a method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements. With a single image and a small amount of annotation, our method creates a physical model of the scene that is suitable for realistically rendering synthetic objects with diffuse, specular, and(More)
In this paper we consider the problem of recovering the free space of an indoor scene from its single image. We show that exploiting the box like geometric structure of furniture and constraints provided by the scene, allows us to recover the extent of major furniture objects in 3D. Our “boxy” detector localizes box shaped objects oriented(More)
Region based features are getting popular due to their higher descriptive power relative to other features. However, real world images exhibit changes in image segments capturing the same scene part taken at different time, under different lighting conditions, from different viewpoints, etc. Segmentation algorithms reflect these changes, and thus(More)
We present a method for automatically creating compact and accurate 3D city models needed for enhanced Augmented Reality applications. The input data are panorama images and LIDAR scans collected at street level and positioned using an IMU and a GPS. Our method corrects for the GPS error and the IMU drift to produce a globally consistent and well registered(More)
We propose a visual recognition approach aimed at fast recognition of urban landmarks on a GPS-enabled mobile device. While most existing methods offload their computation to a server, the latency of an image upload over a slow network can be a significant bottleneck. In this paper, we investigate a new approach to mobile visual recognition that would(More)
An image is nothing but a projection of the physical world around us, where objects do not occur randomly but follow certain spatial rules. Many existing computer vision approaches tend to ignore this aspect of understanding images. In this work, we build representations and propose strategies for exploiting such constraints towards extracting a 3D(More)
We present a system for detecting building entrances in outdoor scenes, an important problem for urban scene understanding. While entrance detection in indoor scenes has received a lot of attention, tackling the problem in outdoor scenes is considerably more complicated and remains largely unexplored. The wide variety of door appearances and geometries,(More)
  • 1