Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Tristan Swedish"'
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::647017e6c89a48c557ee18ba49e7e14c
https://doi.org/10.1109/iccv48922.2021.00259
https://doi.org/10.1109/iccv48922.2021.00259
Publikováno v:
SIGGRAPH Courses
The problem of seeing around corners, often referred in the broader "Non-Line-of-Sight" context, is to use sensed information from directly visible surfaces of an environment to infer properties of the scene not directly visible. For example, the geo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0686e4019e3fe2cf57dfa1e07cb7ba45
https://doi.org/10.1145/3388769.3407534
https://doi.org/10.1145/3388769.3407534
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585259
ECCV (29)
ECCV (29)
We introduce the new non-line-of-sight imaging problem of imaging behind an occluder. The behind-an-occluder problem can be solved if the hidden space is flanked by opposing visible surfaces. We illuminate one surface and observe light that scatters
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1aeb6c5a5d44bd8181aaeb61f42a7580
https://doi.org/10.1007/978-3-030-58526-6_34
https://doi.org/10.1007/978-3-030-58526-6_34
Publikováno v:
Clinical Ophthalmology (Auckland, N.Z.)
Karin Roesch, Tristan Swedish, Ramesh Raskar MIT Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA Abstract: Most current diagnostic devices are expensive, require trained specialists to operate and gather static images with sparse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37629f2e8c77d5b0e103d37cad52f618
https://doi.org/10.2147/opth.s116265
https://doi.org/10.2147/opth.s116265
Autor:
Tristan Swedish, Ramesh Raskar
Publikováno v:
CVPR Workshops
We propose an approach for solving Visual Teach and Repeat tasks for routes that consist of discrete directions along path networks using deep learning. Visual paths are specified by a single monocular image sequence and our approach does not query f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d0e045b5238990f371e6fae6f35f202
https://doi.org/10.1109/cvprw.2018.00203
https://doi.org/10.1109/cvprw.2018.00203
Publikováno v:
Imaging and Applied Optics 2018 (3D, AO, AIO, COSI, DH, IS, LACSEA, LS&C, MATH, pcAOP).
Non-line-of-right (NLOS) imaging has recently been demonstrated using traditional cameras. Here we present a data-driven technique for NLOS imaging. We experimentally analyze the role of scene geometry and clutter on reconstruction quality.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf28c20cfdcfab4854546846c907fd83
https://doi.org/10.1364/isa.2018.iw2b.6
https://doi.org/10.1364/isa.2018.iw2b.6
Publikováno v:
SIGGRAPH Courses
Modeling the human body is of special interest in computer graphics to create "virtual humans", but material and optical properties of biological tissues are complex and not easily captured. This course will cover the major topics and challenges in u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78661f8ed96f8ce6f689ad2059cd62a0
https://doi.org/10.1145/2897826.2927371
https://doi.org/10.1145/2897826.2927371
Publikováno v:
EMBC
MIT web domain
MIT web domain
Medical data presents a number of challenges. It tends to be unstructured, noisy and protected. To train algorithms to understand medical images, doctors can label the condition associated with a particular image, but obtaining enough labels can be d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6b31754f1e280524ebb37b320a70e05
https://pubmed.ncbi.nlm.nih.gov/26738085
https://pubmed.ncbi.nlm.nih.gov/26738085
Publikováno v:
Imaging and Applied Optics 2016.
We demonstrate an endoscopic imaging system for microscopic flow measurement (for example blood flow in tissue) using laser speckle contrast imaging. Computational imaging is used to reject sub-surface scattering and eliminates erroneous flow speed e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3fbf84c79505df8e3a015e7bde16464c
https://doi.org/10.1364/3d.2016.jt3a.29
https://doi.org/10.1364/3d.2016.jt3a.29
Publikováno v:
ICCV
In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing videos that contain a depth map (RGBD) on a 2D screen. Saliency estimation in this scenario is highly important since in the near
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3871ee70fd4c1748d0d859cfe058f5a3