Data-Driven 3D Primitives for Single Image Understanding

Fouhey, David F.; Gupta, Abhinav; Hebert, Martial

doi:10.1109/iccv.2013.421

Cited by 156 publications

(152 citation statements)

References 20 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…Unlike other approaches which incorporate geometry in DPM via CAD models [26] or manually-labeled 3D cuboids [14,18], our approach uses noisy depth data for training (similar to [15]). This allows us to access more and diverse data (hundreds of images compared to 40 or so CAD models).…”

Section: Related Workmentioning

confidence: 99%

Building Part-Based Object Detectors via 3D Geometry

Shrivastava

Gupta

2013

2013 IEEE International Conference on Computer Vision

Self Cite

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Building Part-Based Object Detectors via 3D Geometry

Shrivastava

Gupta

2013

2013 IEEE International Conference on Computer Vision

Self Cite

View full text Add to dashboard Cite

“…Recently, Fouhey et al 14 presented an approach to infer 3-D surface normals from a single image using the primitives that were visually discriminative and geometrically informative. They also introduced mid-level constraints for 3-D scene understanding in the form of convex and concave edges in the study by Fouhey et al 15 Ladicky et al 16 combined contextual and segment-based cues and built a regressor in a boosting framework by transforming the problem into a regression of coefficients of a local coding.…”

Section: Related Workmentioning

confidence: 99%

Fast depth extraction from a single image

Dong

Wang

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Predicting depth from a single image is an important problem for understanding the 3-D geometry of a scene. Recently, the nonparametric depth sampling (DepthTransfer) has shown great potential in solving this problem, and its two key components are a Scale Invariant Feature Transform (SIFT) flow-based depth warping between the input image and its retrieved similar images and a pixel-wise depth fusion from all warped depth maps. In addition to the inherent heavy computational load in the SIFT flow computation even under a coarse-to-fine scheme, the fusion reliability is also low due to the low discriminativeness of pixel-wise description nature. This article aims at solving these two problems. First, a novel sparse SIFT flow algorithm is proposed to reduce the complexity from subquadratic to sublinear. Then, a reweighting technique is introduced where the variance of the SIFT flow descriptor is computed at every pixel and used for reweighting the data term in the conditional Markov random fields. Our proposed depth transfer method is tested on the Make3D Range Image Data and NYU Depth Dataset V2. It is shown that, with comparable depth estimation accuracy, our method is 2-3 times faster than the DepthTransfer.

show abstract

“…Examples of these kinds of relationship at the local level (e.g. dealing with small collections of primitives), include data driven techniques to recognise common configurations of oriented planes [38], or concave/convex edges [5], and recent deep learning approaches which exploit prelearned representations [4]. These data-driven techniques are designed to exploit the recent prevalence of large scale reconstruction datasets, to learn which configurations are the most common and recognisable.…”

Section: Top-down Reconstructionmentioning

confidence: 99%