Search Results for author: Qi-Xing Huang

Found 32 papers, 16 papers with code

A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks

no code implementations ECCV 2020 Sangpil Kim, Hyung-gun Chi, Xiao Hu, Qi-Xing Huang, Karthik Ramani

We introduce a large-scale annotated mechanical components benchmark for classification and retrieval tasks named MechanicalComponents Benchmark (MCB): a large-scale dataset of 3D objects of mechanical components.

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

2 code implementations ECCV 2020 Zaiwei Zhang, Bo Sun, Haitao Yang, Qi-Xing Huang

We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives.

3D Object Detection

HybridPose: 6D Object Pose Estimation under Hybrid Representations

4 code implementations CVPR 2020 Chen Song, Jiaru Song, Qi-Xing Huang

Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e. g., because of occlusion).

6D Pose Estimation using RGB

Extreme Relative Pose Network under Hybrid Representations

1 code implementation CVPR 2020 Zhenpei Yang, Siming Yan, Qi-Xing 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 poses.

Pose Estimation Translation

A Condition Number for Joint Optimization of Cycle-Consistent Networks

1 code implementation NeurIPS 2019 Leonidas J. Guibas, Qi-Xing Huang, Zhenxiao Liang

A recent trend in optimizing maps such as dense correspondences between objects or neural networks between pairs of domains is to optimize them jointly.

Joint Learning of Neural Networks via Iterative Reweighted Least Squares

1 code implementation16 May 2019 Zaiwei Zhang, Xiangru Huang, Qi-Xing Huang, Xiao Zhang, Yuan Li

We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks.

Fine-tuning General Classification +2

Learning Transformation Synchronization

1 code implementation CVPR 2019 Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, Qi-Xing Huang

Our approach alternates between transformation synchronization using weighted relative transformations and predicting new weights of the input relative transformations using a neural network.

Path-Invariant Map Networks

1 code implementation CVPR 2019 Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou, Qi-Xing Huang

Optimizing a network of maps among a collection of objects/domains (or map synchronization) is a central problem across computer vision and many other relevant fields.

3D Semantic Segmentation Scene Segmentation

PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation

1 code implementation CVPR 2019 Sida Peng, Yu-An Liu, Qi-Xing Huang, Hujun Bao, Xiaowei Zhou

We further create a Truncation LINEMOD dataset to validate the robustness of our approach against truncation.

 Ranked #1 on 6D Pose Estimation using RGB on YCB-Video (Mean AUC metric)

6D Pose Estimation using RGB

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

1 code implementation CVPR 2019 Zhenpei Yang, Jeffrey Z. Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman, Qi-Xing Huang

In particular, instead of only performing scene completion from each individual scan, our approach alternates between relative pose estimation and scene completion.

Pose Estimation

Joint Map and Symmetry Synchronization

no code implementations ECCV 2018 Yifan Sun, Zhenxiao Liang, Xiangru Huang, Qi-Xing Huang

Most existing techniques in map computation (e. g., in the form of feature or dense correspondences) assume that the underlying map between an object pair is unique.

Deep Generative Modeling for Scene Synthesis via Hybrid Representations

no code implementations6 Aug 2018 Zaiwei Zhang, Zhenpei Yang, Chongyang Ma, Linjie Luo, Alexander Huth, Etienne Vouga, Qi-Xing Huang

We show a principled way to train this model by combining discriminator losses for both a 3D object arrangement representation and a 2D image-based representation.

SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions

no code implementations ICML 2018 Chandrajit Bajaj, Tingran Gao, Zihang He, Qi-Xing Huang, Zhenxiao Liang

We introduce a principled approach for simultaneous mapping and clustering (SMAC) for establishing consistent maps across heterogeneous object collections (e. g., 2D images or 3D shapes).


StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

1 code implementation ECCV 2018 Xingyi Zhou, Arjun Karpur, Linjie Luo, Qi-Xing Huang

Existing methods define semantic keypoints separately for each category with a fixed number of semantic labels in fixed indices.

Keypoint Detection Viewpoint Estimation

Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency

1 code implementation ECCV 2018 Xingyi Zhou, Arjun Karpur, Chuang Gan, Linjie Luo, Qi-Xing Huang

In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image.

Unsupervised Domain Adaptation

3D Object Classification via Spherical Projections

no code implementations12 Dec 2017 Zhangjie Cao, Qi-Xing Huang, Karthik Ramani

Our main idea is to project a 3D object onto a spherical domain centered around its barycenter and develop neural network to classify the spherical projection.

3D Classification 3D Object Classification +3

Translation Synchronization via Truncated Least Squares

no code implementations NeurIPS 2017 Xiangru Huang, Zhenxiao Liang, Chandrajit Bajaj, Qi-Xing Huang

In this paper, we introduce a robust algorithm, \textsl{TranSync}, for the 1D translation synchronization problem, in which the aim is to recover the global coordinates of a set of nodes from noisy measurements of relative coordinates along an observation graph.


Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

4 code implementations ICCV 2017 Xingyi Zhou, Qi-Xing Huang, Xiao Sun, xiangyang xue, Yichen Wei

We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.

Monocular 3D Human Pose Estimation Pose Prediction +1

Normalized Spectral Map Synchronization

no code implementations NeurIPS 2016 Yanyao Shen, Qi-Xing Huang, Nati Srebro, Sujay Sanghavi

The algorithmic advancement of synchronizing maps is important in order to solve a wide range of practice problems with possible large-scale dataset.

Distributable Consistent Multi-Object Matching

no code implementations CVPR 2018 Nan Hu, Qi-Xing Huang, Boris Thibert, Leonidas Guibas

In this paper we propose an optimization-based framework to multiple object matching.

Symmetry-aware Depth Estimation using Deep Neural Networks

no code implementations20 Apr 2016 Guilin Liu, Chao Yang, Zimo Li, Duygu Ceylan, Qi-Xing Huang

Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications.

Depth Estimation

Learning Dense Correspondence via 3D-guided Cycle Consistency

no code implementations CVPR 2016 Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qi-Xing Huang, Alexei A. Efros

We use ground-truth synthetic-to-synthetic correspondences, provided by the rendering engine, to train a ConvNet to predict synthetic-to-real, real-to-real and real-to-synthetic correspondences that are cycle-consistent with the ground-truth.

Capturing Dynamic Textured Surfaces of Moving Targets

no code implementations11 Apr 2016 Ruizhe Wang, Lingyu Wei, Etienne Vouga, Qi-Xing Huang, Duygu Ceylan, Gerard Medioni, Hao Li

We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals, using only three or four handheld sensors.

Shape and Symmetry Induction for 3D Objects

no code implementations24 Nov 2015 Shubham Tulsiani, Abhishek Kar, Qi-Xing Huang, João Carreira, Jitendra Malik

Actions as simple as grasping an object or navigating around it require a rich understanding of that object's 3D shape from a given viewpoint.

General Classification Object Classification

Dense Human Body Correspondences Using Convolutional Networks

no code implementations CVPR 2016 Lingyu Wei, Qi-Xing Huang, Duygu Ceylan, Etienne Vouga, Hao Li

We propose a deep learning approach for finding dense correspondences between 3D scans of people.

Unsupervised Multi-Class Joint Image Segmentation

no code implementations CVPR 2014 Fan Wang, Qi-Xing Huang, Maks Ovsjanikov, Leonidas J. Guibas

Joint segmentation of image sets is a challenging problem, especially when there are multiple objects with variable appearance shared among the images in the collection and the set of objects present in each particular image is itself varying and unknown.

Semantic Segmentation

Near-Optimal Joint Object Matching via Convex Relaxation

no code implementations6 Feb 2014 Yuxin Chen, Leonidas J. Guibas, Qi-Xing Huang

Joint matching over a collection of objects aims at aggregating information from a large collection of similar instances (e. g. images, graphs, shapes) to improve maps between pairs of them.

Cannot find the paper you are looking for? You can Submit a new open access paper.