• Publications
  • Influence
Photo tourism: exploring photo collections in 3D
We present a system for interactively browsing and exploring large unstructured collections of photographs of a scene using a novel 3D interface. Our system consists of an image-based modeling front
Modeling the World from Internet Photo Collections
This paper presents structure-from-motion and image-based rendering algorithms that operate on hundreds of images downloaded as a result of keyword-based image search queries like “Notre Dame” or “Trevi Fountain,” and presents these algorithms and results as a first step towards 3D modeled sites, cities, and landscapes from Internet imagery.
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
This paper first survey multi-view stereo algorithms and compare them qualitatively using a taxonomy that differentiates their key properties, then describes the process for acquiring and calibrating multiview image datasets with high-accuracy ground truth and introduces the evaluation methodology.
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale
The MegaFace dataset is assembled, both for identification and verification performance, and performance with respect to pose and a persons age is evaluated, as a function of training data size (#photos and #people).
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
This work presents the first dense SLAM system capable of reconstructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sensors, and displays the updated model in real time.
Multicore bundle adjustment
The design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene reconstruction problems and show that overcoming the severe memory and bandwidth limitations of current generation GPUs not only leads to more space efficient algorithms, but also to surprising savings in runtime.
A Theory of Shape by Space Carving
A provably-correct algorithm is given, called Space Carving, for computing the 3D shape of an unknown, arbitrarily-shaped scene from multiple photographs taken at known but arbitrarily-distributed viewpoints to capture photorealistic shapes that accurately model scene appearance from a wide range of viewpoints.
Towards Internet-scale multi-view stereo
An approach for enabling existing multi-view stereo methods to operate on extremely large unstructured photo collections to decompose the collection into a set of overlapping sets of photos that can be processed in parallel, and to merge the resulting reconstructions.
Building Rome in a day
A system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city on Internet photo sharing sites and is designed to scale gracefully with both the size of the problem and the amount of available computation.
Photorealistic Scene Reconstruction by Voxel Coloring
  • S. Seitz, C. Dyer
  • Physics
    International Journal of Computer Vision
  • 17 June 1997
A novel scene reconstruction technique is presented, different from previous approaches in its ability to cope with large changes in visibility and its modeling of intrinsic scene color and texture