Building Rome on a Cloudless Day

Frahm, Jan‐Michael; Fite-Georgel, Pierre; Gallup, David; Johnson, Tim; Raguram, Rahul; Wu, Cindy; Jen, Yi-Hung; Dunn, Enrique; Clipp, Brian; Lazebnik, Svetlana; Pollefeys, Marc

doi:10.1007/978-3-642-15561-1_27

Cited by 440 publications

(382 citation statements)

References 31 publications

Supporting

Mentioning

377

Contrasting

Unclassified

Order By: Relevance

“…As our method is a post-processing step for SfM, we require as input typical outputs of such a system [2,11,24,27]. In our results we used [27] and [24].…”

Section: Step : Input Reconstructionmentioning

confidence: 99%

“…The achieved progress is impressive and has enabled largescale scene reconstruction from thousands of images covering different scenes around the world [2,9,11,27]. In crowd-sourced reconstructions of large-scale environments, SfM methods do not have any control over the acquisition of the images, leading to many new challenges.…”

Section: Introductionmentioning

confidence: 99%

“…However, the decision of which image to add next to the reconstruction is not arbitrary. This choice is typically driven by an image similarity metric used to find images that are similar to the ones already registered [2,4,7,11,18,20]. It is within this process that sometimes SfM algorithms select images which do not actually overlap with the current reconstruction, but do overlap with a different instance of the duplicate structure.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction

Heinly

Dunn

Frahm

2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Structure from motion (SfM) is a common technique to recover 3D geometry and camera poses from sets of images of a common scene. In many urban environments, however, there are symmetric, repetitive, or duplicate structures that pose challenges for SfM pipelines. The result of these ambiguous structures is incorrectly placed cameras and points within the reconstruction. In this paper, we present a postprocessing method that can not only detect these errors, but successfully resolve them. Our novel approach proposes the strong and informative measure of conflicting observations, and we demonstrate that it is robust to a large variety of scenes.

show abstract

“…As our method is a post-processing step for SfM, we require as input typical outputs of such a system [2,11,24,27]. In our results we used [27] and [24].…”

Section: Step : Input Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction

Heinly

Dunn

Frahm

2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are methods based on triangulations, such as using laser light [9], structured light [12], coded light [13], and image measurements [6,7,8]. There are also methods do not require triangulations and directly estimate surface normal vectors, such as shape form texture [10] and shape from 2D edge gradients [11].…”

Section: Introductionmentioning

confidence: 99%

High-Definition 3D Reconstruction in Real-Time from a Moving Depth Sensor

Hu¹,

Yu²,

Wang³

2013

Proceedings of the 2013 International Conference on Advanced Computer Science and Electronics Information

View full text Add to dashboard Cite

-This paper proposes a method to reconstruct 3D point clouds of a static scene in real-time by a moving depth sensor. Based on a base-line 3D reconstruction algorithm which fuses depth maps from the moving camera, a depth map enhancement module is embedded in the depth fusion stage to improve the level of details of reconstructed 3D models. Depth enhancements using the Sobel operator and the Laplacian operator are applied for speed and quality considerations. Experiments for real-time reconstruction of 3D scenes, especially the reconstruction of 3D human faces are provided to validate the proposed method. The reconstruction results are inspiring in their high definition compared with the original base-line algorithm.Index Terms -3D reconstruction, Real-time reconstruction, Depth enhancement, High-definition, Depth sensor. I . IntroductionHigh-quality 3D polygonal models reconstructed and rendered from a real world scene are required in different applications, like video-games, movies, virtual reality, ecommerce and other graphics applications. However the generation of a 3D model with precise surface from unorganized point clouds derived from laser scanner data [5] or photogrammetric image measurements [4,6] is a difficult problem. For the reconstruction of a person's face more level of details and capturing time are required to get data, but it feels uncomfortable for people to keep a pose too long; small movements are inevitable.A number of methods have been developed for 3D reconstructions using data from different deceives. There are methods based on triangulations, such as using laser light [9], structured light [12], coded light [13], and image measurements [6,7,8]. There are also methods do not require triangulations and directly estimate surface normal vectors, such as shape form texture [10] and shape from 2D edge gradients [11].The methods based on 3D active sensors (mainly laser scanners) provide the highest quality of reconstruction at present. However, the 3D active sensors are quite expensive, which are mainly for industry applications. Passive imagebased methods using projective geometry [6] are very portable and the sensors are not expensive. But the accuracy of result is low and it cannot satisfy real-time applications.The Kinect Fusion system [1] developed by Microsoft Research uses low-cost depth sensor (the Kinect) and commodity graphics hardware for accurate and real-time 3D reconstruction. Depth data from Kinect is used to track the 3D pose of the sensor and reconstruct 3D models of the physical scene [2]. The advantage of Kinect Fusion is its speed for permitting direct feedback and user interaction. But it is still required to improve the resolution of 3D reconstruction in Kinect Fusion since the hardware performance is generally limited.In this paper, we shall use a depth map enhancement module to improve the quality of the base-line algorithm of Kinect Fusion. We shall apply image enhancement approaches for depth map enhancement. We implement the 3D reconstruction of face model...

show abstract

“…One of these methods is the approach of Kolev et al [11], which we use as a basis for our approach. On the other hand, structure from motion approaches allow to estimate camera poses and sparse point clouds even from unordered photo collections [16,4].…”

Section: Introductionmentioning

confidence: 99%

Dense 3D Reconstruction with a Hand-Held Camera

Ummenhofer

Brox

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we present a method for dense 3D reconstruction from videos where object silhouettes are hard to retrieve. We introduce a close coupling between sparse bundle adjustment and dense multiview reconstruction, which includes surface constraints by the sparse point cloud and an implicit loop closing via the dense surface. The surface is computed in a volumetric framework and guarantees a dense surface without holes. We demonstrate the flexibility of the approach on indoor and outdoor scenes recorded with a commodity hand-held camera.

show abstract

Building Rome on a Cloudless Day

Cited by 440 publications

References 31 publications

Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction

Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction

High-Definition 3D Reconstruction in Real-Time from a Moving Depth Sensor

Dense 3D Reconstruction with a Hand-Held Camera

Contact Info

Product

Resources

About