Mixing synthetic and video images of an outdoor urban environment

Berger, Marie-Odile; Wrobel-Dautcourt, Brigitte; Petitjean, Sylvain; Simon, Gilles

doi:10.1007/s001380050098

Cited by 17 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…and use it to compute ΣΘ vp using Equation 3. The next steps in the calibration process are calculations of the various parameters using deterministic non-linear functions of the vanishing points.…”

Section: Analytical Estimation Of Covariancementioning

confidence: 99%

See 1 more Smart Citation

Placing three-dimensional models in an uncalibrated single image of an architectural scene

Keren

Shimshoni

Tal

2002

Proceedings of the ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

This paper discusses the problem of inserting three-dimensional models into a single image. The main focus of the paper is on the accurate recovery of the camera's parameters, so that 3D models can be inserted in the "correct" position and orientation. An important aspect of this paper is a theoretical and an experimental analysis of the errors. We also implemented a system which "plants" virtual 3D objects in the image, and tested the system on many indoor augmented reality scenes. Our analysis and experiments have shown that errors in the placement of the objects are un-noticeable.

show abstract

Section: Analytical Estimation Of Covariancementioning

confidence: 99%

“…A common approach is to create a new image of a scene from several other images of that scene taken from different viewpoints [6,19]. Another approach is to insert 3D models into video sequences [3,17,9,15]. We deal with a different problem -that of inserting 3D models into a single image.…”

Section: Introductionmentioning

confidence: 99%

Placing three-dimensional models in an uncalibrated single image of an architectural scene

Keren

Shimshoni

Tal

2002

Proceedings of the ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

show abstract

“…A basic problem in many augmented reality systems is creating new artificial images given real images [Azuma 1997;Berger et al 1999;Debevec 1998;Keren et al 2004]. Texture replacement is a challenging example of this type, which can be utilized in other applications, such as post-production in the entertainment industry.…”

Section: Introductionmentioning

confidence: 99%

Image-based texture replacement using multiview images

Tal

Shimshoni

Tal

2008

Proceedings of the 2008 ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

Augmented reality is concerned with combining real-world data, such as images, with artificial data. Texture replacement is one such task. It is the process of painting a new texture over an existing textured image patch, such that depth cues are maintained. This paper proposes a general and automatic approach for performing texture replacement, which is based on multiview stereo techniques that produce depth information at every pixel. The use of several images allows us to address the inherent limitation of previous studies, which are constrained to specific texture classes, such as textureless or near-regular textures. To be able to handle general textures, a modified dense correspondence estimation algorithm is designed and presented.

show abstract

“…The Texture Painter can be made more advanced [1,4], but the aim was to make a simple, low-cost solution, which can be setup anywhere straightforward by non-expert users. Furthermore, the object geometry is not needed which speeds up the process and allows rapid and straightforward experiments.…”

Section: User Interfacementioning

confidence: 99%

“…However, the created virtual environment is still "simpler" than the real world. Unlike VR, Augmented Reality (AR) enables the user to interact with virtual objects and real objects in a real environment in real time [1]. The user can experience enhanced reality by adding virtual objects and by superimposing the computer generated information such as text or graphics onto real objects.…”

Section: Introductionmentioning

confidence: 99%