DEEPFOCAL: A method for direct focal length estimation

Workman, Scott; Greenwell, Connor; Zhai, Menghua; Baltenberger, Ryan; Jacobs, Nathan

doi:10.1109/icip.2015.7351024

Cited by 80 publications

(50 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning to predict the camera intrinsics has mostly been limited to strongly supervised approaches. The sources of groundtruth varies: Workman et al [41] use focal lengths estimated employing classical 1D structure from motion. Yan et al [43] obtain the focal length based on EXIF.…”

Section: Related Workmentioning

confidence: 99%

“…Since the groundtruth values were not accompanied by tolerances, it is hard to tell if the differences are within tolerance or not. Learning and generalization Prior work [41,43,4] Learning of depth, egomotion and intrinsics was done separately on each of the 11 datasets, using monocular images ("cam0") only. Constancy of the intrinsics throughout each dataset separately was imposed, and statistics (mean and standard deviation) for each intrinsic parameter were collected across the results.…”

Section: Camera Intrinsics Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras

Gordon

Jonschkowski

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

366

267

View full text Add to dashboard Cite

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our method learns by applying differentiable warping to frames and comparing the result to adjacent ones, but it provides several improvements: We address occlusions geometrically and differentiably, directly using the depth maps as predicted during training. We introduce randomized layer normalization, a novel powerful regularizer, and we account for object motion relative to the scene. To the best of our knowledge, our work is the first to learn the camera intrinsic parameters, including lens distortion, from video in an unsupervised manner, thereby allowing us to extract accurate depth and motion from arbitrary videos of unknown origin at scale. We evaluate our results on the Cityscapes, KITTI and Eu-RoC datasets, establishing new state of the art on depth prediction and odometry, and demonstrate qualitatively that depth prediction can be learned from a collection of YouTube videos.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Camera Intrinsics Evaluationmentioning

confidence: 99%

Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras

Gordon

Jonschkowski

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

366

267

View full text Add to dashboard Cite

show abstract

“…Thus, recent works estimate the focal length from RGB images without requiring particular geometric structures using deep learning [46,47]. In this work, we take a similar approach.…”

Section: Focal Length Estimationmentioning

confidence: 99%

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild

Grabner

Roth

Lepetit

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We present a joint 3D pose and focal length estimation approach for object categories in the wild. In contrast to previous methods that predict 3D poses independently of the focal length or assume a constant focal length, we explicitly estimate and integrate the focal length into the 3D pose estimation. For this purpose, we combine deep learning techniques and geometric algorithms in a two-stage approach: First, we estimate an initial focal length and establish 2D-3D correspondences from a single RGB image using a deep network. Second, we recover 3D poses and refine the focal length by minimizing the reprojection error of the predicted correspondences. In this way, we exploit the geometric prior given by the focal length for 3D pose estimation. This results in two advantages: First, we achieve significantly improved 3D translation and 3D pose accuracy compared to existing methods. Second, our approach finds a geometric consensus between the individual projection parameters, which is required for precise 2D-3D alignment. We evaluate our proposed approach on three challenging real-world datasets (Pix3D, Comp, and Stanford) with different object categories and significantly outperform the state-of-the-art by up to 20% absolute in multiple different metrics.

show abstract

“…Workman et al [35] use this approach to predict a camera's focal length by estimating the field of view directly from an image using a CNN. However, since they only predict horizontal field of view, they assume that the camera has equal focal length on both the axes which may not be true.…”

Section: Related Workmentioning

confidence: 99%

“…Acknowledgements: We would like to thank Nathan Jacobs for his help in sharing the DeepFocal [35] dataset. We are grateful for financial support from the Programme Grant Seebibyte EP/M013774/1.…”

mentioning

confidence: 99%

A Geometric Approach to Obtain a Bird's Eye View From an Image

Abbas

Zisserman

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

The objective of this paper is to rectify any monocular image by computing a homography matrix that transforms it to a bird's eye (overhead) view.We make the following contributions: (i) we show that the homography matrix can be parameterised with only four parameters that specify the horizon line and the vertical vanishing point, or only two if the field of view or focal length is known; (ii) We introduce a novel representation for the geometry of a line or point (which can be at infinity) that is suitable for regression with a convolutional neural network (CNN); (iii) We introduce a large synthetic image dataset with ground truth for the orthogonal vanishing points, that can be used for training a CNN to predict these geometric entities; and finally (iv) We achieve state-of-theart results on horizon detection, with 74.52% AUC on the Horizon Lines in the Wild dataset. Our method is fast and robust, and can be used to remove perspective distortion from videos in real time.

show abstract

DEEPFOCAL: A method for direct focal length estimation

Cited by 80 publications

References 31 publications

Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras

Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild

A Geometric Approach to Obtain a Bird's Eye View From an Image

Contact Info

Product

Resources

About