activity
20192021
most citedDeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

36 citations · 60 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV20214 cited

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

Jiahui Huang, He Wang, Tolga Birdal +4

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial chal…

cs.CV20203 cited

DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors

Jiahui Huang, Shi-Sheng Huang, Haoxuan Song +1

Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry…

cs.CV2020

Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning

Kshitij Dwivedi, Jiahui Huang, Radoslaw Martin Cichy +1

In this paper, we tackle an open research question in transfer learning, which is selecting a model initialization to achieve high performance on a new task, given several pre-trai…

cs.CV2020

ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings

Jiahui Huang, Sheng Yang, Tai-Jiang Mu +1

We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous solutions…

cs.CV202017 cited

Shallow2Deep: Indoor Scene Modeling by Single Image Understanding

Yinyu Nie, Shihui Guo, Jian Chang +4

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling app…

cs.CV2019

Deep Anchored Convolutional Neural Networks

Jiahui Huang, Kshitij Dwivedi, Gemma Roig

Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. State-of-the-art methods favor such deep network architectures fo…