|
|
Canonical Capsules: Unsupervised Capsules in Canonical Pose
Weiwei Sun*,
Andrea Tagliasacchi*,
Boyang Deng,
Sara Sabour,
Soroosh Yazdani,
Geoffrey Hinton,
Kwang Moo Yi
NeurIPS, 2021
project page |
paper |
code |
bibtex
Learning canonical coordinate frames for 3D point clouds and alignments from a random
coordinate frame to this frame without supervision.
|
|
|
Revisiting 3D Object Detection From an Egocentric Perspective
Boyang Deng,
Charles R. Qi,
Mahyar Najibi,
Thomas Funkhouser,
Yin Zhou,
Dragomir Anguelov
NeurIPS, 2021
paper |
bibtex
Measuring 3D object detection egocentrically via Support Distance Error (SDE) and representing object by star-shaped polygons (StarPoly).
|
|
|
NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
Xiuming Zhang,
Pratul Srinivasan,
Boyang Deng,
Paul Debevec,
William T. Freeman,
Jonathan T. Barron
SIGGRAPH Asia, 2021
project page |
paper |
video |
bibtex
Recovering NeRF-like models of the intrinsics of a scene from a fixed-lighting multi-image capture, by placing priors on illumination and materials.
|
|
|
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis
Pratul Srinivasan,
Boyang Deng,
Xiuming Zhang,
Matthew Tancik,
Ben Mildenhall,
Jonathan T. Barron
CVPR, 2021
project page |
paper |
video |
bibtex
Approximately shading each point in a scene volume using reflectance and visibility fields,
leading to a relightable 3D scene learned from images.
|
|
|
Offboard 3D Object Detection from Point Cloud Sequences
Charles R. Qi,
Yin Zhou,
Mahyar Najibi,
Pei Sun,
Khoa Vo,
Boyang Deng,
Dragomir Anguelov
CVPR, 2021
paper |
blog post |
bibtex
Proposing a high quality offboard 3D object detection pipeline using point cloud sequence data.
|
