1 code implementation • 31 Jan 2024 • Tien Do, Sudipta N. Sinha
To mitigate the capacity issue, we propose to split the landmarks into subgroups and train a separate network for each subgroup.
1 code implementation • 2 Nov 2022 • Qiangqiang Huang, Joseph DeGol, Victor Fragoso, Sudipta N. Sinha, John J. Leonard
Our main contribution is a novel framework for modeling camera localizability that incorporates both natural scene features and artificial fiducial markers added to the scene.
no code implementations • CVPR 2022 • Tien Do, Ondrej Miksik, Joseph DeGol, Hyun Soo Park, Sudipta N. Sinha
Our key idea is to implicitly encode the appearance of a sparse yet salient set of 3D scene points into a convolutional neural network (CNN) that can detect these scene points in query images whenever they are visible.
1 code implementation • CVPR 2021 • Jae Yong Lee, Joseph DeGol, Victor Fragoso, Sudipta N. Sinha
We address estimating dense correspondences between two images depicting different but semantically related scenes.
no code implementations • CVPR 2021 • Mihai Dusmanu, Johannes L. Schönberger, Sudipta N. Sinha, Marc Pollefeys
Many computer vision systems require users to upload image features to the cloud for processing and storage.
1 code implementation • CVPR 2020 • Sena Kiciroglu, Helge Rhodin, Sudipta N. Sinha, Mathieu Salzmann, Pascal Fua
The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured.
no code implementations • CVPR 2019 • Francesco Pittaluga, Sanjeev J. Koppal, Sing Bing Kang, Sudipta N. Sinha
We present a privacy attack that reconstructs color images of the scene from the point cloud.
no code implementations • CVPR 2019 • Pablo Speciale, Johannes L. Schönberger, Sing Bing Kang, Sudipta N. Sinha, Marc Pollefeys
Current localization systems rely on the persistent storage of 3D point clouds of the scene to enable camera pose estimation, but such data reveals potentially sensitive scene information.
no code implementations • 9 Feb 2019 • Tomas Hodan, Vibhav Vineet, Ran Gal, Emanuel Shalev, Jon Hanzelka, Treb Connell, Pedro Urbina, Sudipta N. Sinha, Brian Guenter
We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images.
no code implementations • ECCV 2018 • Johannes L. Schonberger, Sudipta N. Sinha, Marc Pollefeys
Semi-Global Matching (SGM) uses an aggregation scheme to combine costs from multiple 1D scanline optimizations that tends to hurt its accuracy in difficult scenarios.
no code implementations • 4 Aug 2018 • Jing Dong, Byron Boots, Frank Dellaert, Ranveer Chandra, Sudipta N. Sinha
Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences.
no code implementations • ECCV 2018 • Benjamin Hepp, Debadeepta Dey, Sudipta N. Sinha, Ashish Kapoor, Neel Joshi, Otmar Hilliges
We propose to learn a better utility function that predicts the usefulness of future viewpoints.
no code implementations • 3 Dec 2017 • Daniel Scharstein, Tatsunori Taniai, Sudipta N. Sinha
In this paper we evaluate plane orientation priors derived from stereo matching at a coarser resolution and show that such priors can yield significant performance gains for difficult weakly-textured scenes.
5 code implementations • CVPR 2018 • Bugra Tekin, Sudipta N. Sinha, Pascal Fua
For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches when they are all used without post-processing.
Ranked #1 on 6D Pose Estimation using RGB on OCCLUSION
no code implementations • CVPR 2017 • Tatsunori Taniai, Sudipta N. Sinha, Yoichi Sato
This unified framework benefits all four tasks - stereo, optical flow, visual odometry and motion segmentation leading to overall higher accuracy and efficiency.
no code implementations • CVPR 2017 • Artem Rozantsev, Sudipta N. Sinha, Debadeepta Dey, Pascal Fua
Our main contribution is a new bundle adjustment procedure which in addition to optimizing the camera poses, regularizes the point trajectory using a prior based on motion dynamics (or specifically flight dynamics).
no code implementations • CVPR 2016 • Tatsunori Taniai, Sudipta N. Sinha, Yoichi Sato
We propose a new technique to jointly recover cosegmentation and dense per-pixel correspondence in two images.
no code implementations • CVPR 2016 • Jaesik Park, Yu-Wing Tai, Sudipta N. Sinha, In So Kweon
We present a robust low-rank matrix factorization method to estimate the unknown parameters of this model.
no code implementations • CVPR 2014 • Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
We show that a non-isotropic near point light source rigidly attached to a camera can be calibrated using multiple images of a weakly textured planar scene.
no code implementations • CVPR 2014 • Sudipta N. Sinha, Daniel Scharstein, Richard Szeliski
We present a stereo algorithm designed for speed and efficiency that uses local slanted plane sweeps to propose disparity hypotheses for a semi-global matching algorithm.
no code implementations • CVPR 2013 • Alessandro Bergamo, Sudipta N. Sinha, Lorenzo Torresani
In this paper we propose a new technique for learning a discriminative codebook for local feature descriptors, specifically designed for scalable landmark classification.