21 citations · 49 across the 9 of their papers we have counts for
9 papers
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction
Zhenpei Yang, Zaiwei Zhang, Qixing Huang
Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic…
FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
Zhenpei Yang, Zhile Ren, Miguel Angel Bautista +3
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate cam…
Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
Siming Yan, Zhenpei Yang, Haoxiang Li +5
This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation,…
HPNet: Deep Primitive Segmentation Using Hybrid Representations
Siming Yan, Zhenpei Yang, Chongyang Ma +3
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is…
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
Zhenpei Yang, Zhile Ren, Qi Shan +1
Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution o…
SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
Zhenpei Yang, Yuning Chai, Dragomir Anguelov +5
Autonomous driving system development is critically dependent on the ability to replay complex and diverse traffic scenarios in simulation. In such scenarios, the ability to accura…
Extreme Relative Pose Network under Hybrid Representations
Zhenpei Yang, Siming Yan, Qixing Huang
In this paper, we introduce a novel RGB-D based relative pose estimation approach that is suitable for small-overlapping or non-overlapping scans and can output multiple relative p…
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Zhenpei Yang, Jeffrey Z. Pan, Linjie Luo +3
Estimating the relative rigid pose between two RGB-D scans of the same underlying environment is a fundamental problem in computer vision, robotics, and computer graphics. Most exi…
Deep Generative Modeling for Scene Synthesis via Hybrid Representations
Zaiwei Zhang, Zhenpei Yang, Chongyang Ma +4
We present a deep generative scene modeling technique for indoor environments. Our goal is to train a generative model using a feed-forward neural network that maps a prior distrib…