activity
20172021
most citedPeephole: Predicting Network Performance Before Training

84 citations · 95 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2021

Offboard 3D Object Detection from Point Cloud Sequences

Charles R. Qi, Yin Zhou, Mahyar Najibi +4

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, suc…

cs.CV20205 cited

NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis

Pratul P. Srinivasan, Boyang Deng, Xiuming Zhang +3

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from…

cs.CV2019

CvxNet: Learnable Convex Decomposition

Boyang Deng, Kyle Genova, Soroosh Yazdani +3

Any solid object can be decomposed into a collection of convex polytopes (in short, convexes). When a small number of convexes are used, such a decomposition can be thought of as a…

cs.CV20196 cited

Cerberus: A Multi-headed Derenderer

Boyang Deng, Simon Kornblith, Geoffrey Hinton

To generalize to novel visual scenes with new viewpoints and new object poses, a visual system needs representations of the shapes of the parts of an object that are invariant to c…

cs.CV2018

BlockQNN: Efficient Block-wise Neural Network Architecture Generation

Zhao Zhong, Zichen Yang, Boyang Deng +4

Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and ela…

cs.LG201784 cited

Peephole: Predicting Network Performance Before Training

Boyang Deng, Junjie Yan, Dahua Lin

The quest for performant networks has been a significant force that drives the advancements of deep learning in recent years. While rewarding, improving network design has never be…