11 citations · 39 across the 12 of their papers we have counts for
13 papers
SuperUDF: Self-supervised UDF Estimation for Surface Reconstruction
Hui Tian, Chenyang Zhu, Yifei Shi +1
Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF lear…
RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
Yifei Shi, Junhua Xi, Dewen Hu +2
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of ou…
Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
Yi Sun, Xin Xu, Jian Li +3
Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task infere…
SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations
Boyan Wan, Yifei Shi, Kai Xu
Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become i…
RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
Junhua Xi, Yifei Shi, Yijie Wang +2
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of ou…
3DRM:Pair-wise relation module for 3D object detection
Yuqing Lan, Yao Duan, Yifei Shi +2
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for…
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
Yifei Shi, Junwen Huang, Xin Xu +2
We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from…
CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels
Yongqian Xiao, Xin Xu, QianLi Lin
With the development of end-to-end control based on deep learning, it is important to study new system modeling techniques to realize dynamics modeling with high-dimensional inputs…
SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
Yifei Shi, Junwen Huang, Hongjia Zhang +3
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an en…
Rescan: Inductive Instance Segmentation for Indoor RGBD Scans
Maciej Halber, Yifei Shi, Kai Xu +1
In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of re…
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
Yifei Shi, Angel Xuan Chang, Zhelun Wu +2
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a…
PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction
Yifei Shi, Kai Xu, Matthias Niessner +2
We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in…
Recurrent 3D Attentional Networks for End-to-End Active Object Recognition
Min Liu, Yifei Shi, Lintao Zheng +3
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the…