papers

Publications (7)

cs.CV2021

FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation

Zirui Wang, Shuda Li, Henry Howard-Jenkins +2

We present FlowNet3D++, a deep scene flow estimation network. Inspired by classical methods, FlowNet3D++ incorporates geometric constraints in the form of point-to-plane distance a…

cs.CV2016

HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor

Shuda Li, Ankur Handa, Yang Zhang +1

We describe a new method for comparing frame appearance in a frame-to-model 3-D mapping and tracking system using an low dynamic range (LDR) RGB-D camera which is robust to brightn…

cs.CV2022

SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms

Shuai Su, Zhongkai Zhao, Yixin Fei +3

Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise r…

cs.CV2021

Resolution Correspondence Networks

Georgi Tinchev, Shuda Li, Kai Han +2

In this paper, we aim at establishing accurate dense correspondences between a pair of images with overlapping field of view under challenging illumination variation, viewpoint cha…

cs.CV2020

Dual-Resolution Correspondence Networks

Xinghui Li, Kai Han, Shuda Li +1

We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to…

cs.CV2020

Correspondence Networks with Adaptive Neighbourhood Consensus

Shuda Li, Kai Han, Theo W. Costain +2

In this paper, we tackle the task of establishing dense visual correspondences between images containing objects of the same category. This is a challenging task due to large intra…

cs.CV2019

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

Henry Howard-Jenkins, Shuda Li, Victor Prisacariu

We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference pro…