CVPR Best Papers CollectingCVPR is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.
CVPR, pp.6800-6809, (2019)
Some of the source photons are reflected by the visible scene toward parts—say, the back of an object facing a camera, an object around a corner, or an object viewed through a diffuser — that are hidden from the direct line of sight of the camera
Cited by43BibtexViews93Links
0
0
CVPR, pp.1-10, (2019)
We have presented a method that can learn a 3D model of a deformable object category from an unconstrained collection of single-view images of the object category
Cited by4BibtexViews500Links
0
0
CVPR, pp.42-51, (2019)
We show that the reconstruction quality by BSP-Net is competitive with state-of-the-art methods while using much fewer primitives
Cited by3BibtexViews144Links
0
0
international joint conference on artificial intelligence, (2018): 3712-3722
This is the basis of our approach: we computes an affinity matrix among tasks based on whether the solution for one task can be sufficiently read out of the representation trained for another task. Such transfers are exhaustively sampled, and a Binary Integer Programming formulat...
Cited by284BibtexViews132Links
0
0
CVPR, (2017)
Because we adopted hyperparameter settings optimized for residual networks in our study, we believe that further gains in accuracy of DenseNets may be obtained by more detailed tuning of hyperparameters and learning rate schedules
Cited by6524BibtexViews184Links
0
0
Abhishek Shrivastava, Tomas Pfister,Oncel Tuzel,Josh Susskind, Wenda Wang, Russell Y. Webb
computer vision and pattern recognition, (2017)
Training on refined synthetic data – the output of SimGAN which does not require any labeling for the real images – outperforms the model trained on real images with supervision, by 8.8%
Cited by1015BibtexViews94Links
0
0
CVPR, (2016)
Deep networks naturally integrate low/mid/highlevel features and classifiers in an end-to-end multilayer fashion, and the “levels” of features can be enriched by the number of stacked layers
Cited by47481BibtexViews1202Links
0
0
IEEE Conference on Computer Vision and Pattern Recognition, (2015)
In this paper we introduced DynamicFusion, the first real-time dense dynamic scene reconstruction system, removing the static scene assumption pervasive across realtime 3D reconstruction and SLAM systems
Cited by528BibtexViews92Links
0
0
CVPR, pp.2179-2186, (2014)
Recent works in computer vision show that differential motion of the light source or the object inform about shape even with unknown bidirectional reflectance distribution function
Cited by18BibtexViews66Links
0
0
CVPR, pp.1814-1821, (2013)
We demonstrate the efficacy of the approach by scaling object detection to one hundred thousand object classes employing millions of filters representing objects and their constituent parts across a wide range of poses and scales
Cited by322BibtexViews118Links
0
0
International Journal of Computer Vision, no. 2 (2012): 101-122
This paper proposes a simple "prior-free" method for solving the non-rigid structure-from-motion (NRSfM) factorization problem. Other than using the fundamental low-order linear combination model assumption, our method does not assume any extra prior knowledge either about the no...
Cited by208BibtexViews49Links
0
0
Single image haze removal using dark channel prior, (2011)
We have proposed a very simple but powerful prior, called dark channel prior, for single image haze removal
Cited by3290BibtexViews293Links
0
0
Computer Vision and Pattern Recognition, pp.1297-1304, (2011)
We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation prob...
Cited by10BibtexViews63Links
0
0
Computer Vision and Pattern Recognition, pp.771-778, (2010)
The calculation of a low-rank approximation of a matrix is a fundamental operation in many computer vision applications. The workhorse of this class of problems has long been the Singular Value Decomposition. However, in the presence of missing data and outliers this method is no...
Cited by177BibtexViews45Links
0
0
International Journal of Computer Vision, no. 1 (2008): 3-15
We provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint
Cited by1071BibtexViews52Links
0
0
CVPR, (2008)
The gain in speed and robustness allows the use of better local classifiers, for which we demonstrated excellent results on the UIUC Cars, the PASCAL VOC 2006 dataset and in the VOC 2007 challenge
Cited by901BibtexViews61Links
0
0
Anchorage, AK, pp.1-8, (2008)
Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph-cuts, has not been able to incorporate second-order priors because the triple cliques...
Cited by403BibtexViews50Links
0
0
CVPR, (2007)
We have presented an integrated system for dynamic 3D scene analysis from a moving platform
Cited by387BibtexViews56Links
0
0
CVPR (1), pp.822-828, (2005)
We have demonstrated a very fast and robust approach to detecting deformable surfaces
Cited by132BibtexViews49Links
0
0
CVPR (1), pp.436-443, (2004)
In this paper, we introduce the notion of a pro- grammable imaging system. Such an imaging system provides a human user or a vision system significant control over the radiometric and geometric characteris- tics of the system. This flexibility is achieved using a programmable arr...
Cited by162BibtexViews56Links
0
0