no code implementations • 1 Jun 2023 • Weiyu Li, Xuelin Chen, Peizhuo Li, Olga Sorkine-Hornung, Baoquan Chen
At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches.
no code implementations • 17 May 2023 • Yingda Yin, Jiangran Lyu, Yang Wang, He Wang, Baoquan Chen
With this benefit, we demonstrate its advantages in semi-supervised rotation regression, where the pseudo labels are noisy.
no code implementations • CVPR 2023 • Weiyu Li, Xuelin Chen, Jue Wang, Baoquan Chen
We target a 3D generative model for general natural scenes that are typically unique and intricate.
no code implementations • 13 Apr 2023 • Jiatao Gu, Qingzhe Gao, Shuangfei Zhai, Baoquan Chen, Lingjie Liu, Josh Susskind
To address these challenges, We present Control3Diff, a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile, controllable 3D-aware image synthesis for single-view datasets.
1 code implementation • CVPR 2023 • Yulin Liu, Haoran Liu, Yingda Yin, Yang Wang, Baoquan Chen, He Wang
Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data.
no code implementations • 3 Mar 2023 • Yingda Yin, Yang Wang, He Wang, Baoquan Chen
Rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region, resulting in a better convergence.
no code implementations • 12 Oct 2022 • Heyuan Yao, Zhenhua Song, Baoquan Chen, Libin Liu
Our framework can learn a rich and flexible latent representation of skills and a skill-conditioned generative control policy from a diverse set of unorganized motion sequences, which enables the generation of realistic human behaviors by sampling in the latent space and allows high-level control policies to reuse the learned skills to accomplish a variety of downstream tasks.
1 code implementation • 4 Oct 2022 • Tenglong Ao, Qingzhe Gao, Yuke Lou, Baoquan Chen, Libin Liu
We present a novel co-speech gesture synthesis method that achieves convincing results both on the rhythm and semantics.
Ranked #1 on Gesture Generation on TED Gesture Dataset
no code implementations • 3 Oct 2022 • Yujie Wang, Xuelin Chen, Baoquan Chen
We present a 3D generative model for general natural scenes.
no code implementations • 25 Aug 2022 • Yiming Wang, Qingzhe Gao, Libin Liu, Lingjie Liu, Christian Theobalt, Baoquan Chen
The learned representation can be used to synthesize novel view images of an arbitrary person from a sparse set of cameras, and further animate them with the user's pose control.
1 code implementation • 14 Aug 2022 • Siyan Dong, Shuzhe Wang, Yixin Zhuang, Juho Kannala, Marc Pollefeys, Baoquan Chen
Visual (re)localization addresses the problem of estimating the 6-DoF (Degree of Freedom) camera pose of a query image captured in a known scene, which is a key building block of many computer vision and robotics applications.
no code implementations • CVPR 2022 • Kai Ye, Siyan Dong, Qingnan Fan, He Wang, Li Yi, Fei Xia, Jue Wang, Baoquan Chen
Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction.
no code implementations • CVPR 2022 • Yingda Yin, Yingcheng Cai, He Wang, Baoquan Chen
Inspired by the popular semi-supervised approach, FixMatch, we propose to leverage pseudo label filtering to facilitate the information flow from labeled data to unlabeled data in a teacher-student mutual learning framework.
1 code implementation • 8 Feb 2022 • Yunzhe Liu, Rinon Gal, Amit H. Bermano, Baoquan Chen, Daniel Cohen-Or
We compare our models to a wide range of latent editing methods, and show that by alleviating the bias they achieve finer semantic control and better identity preservation through a wider range of transformations.
1 code implementation • CVPR 2022 • Jiayi Chen, Yingda Yin, Tolga Birdal, Baoquan Chen, Leonidas Guibas, He Wang
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem.
1 code implementation • 10 Jun 2021 • Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen
Co-part segmentation is an important problem in computer vision for its rich applications.
no code implementations • 8 Jun 2021 • Xuelin Chen, Weiyu Li, Daniel Cohen-Or, Niloy J. Mitra, Baoquan Chen
In this paper, we introduce Neural Motion Consensus Flow (MoCo-Flow), a representation that models dynamic humans in stationary monocular cameras using a 4D continuous time-variant function.
1 code implementation • 6 Jun 2021 • Yixin Zhuang, Yunzhe Liu, Yujie Wang, Baoquan Chen
However, the image features for describing 3D point samplings of implicit functions are less effective when significant variations of occlusions, views, and appearances exist from the image.
1 code implementation • 6 May 2021 • Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, Baoquan Chen
Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning.
1 code implementation • ICCV 2021 • Yijia Weng, He Wang, Qiang Zhou, Yuzhe Qin, Yueqi Duan, Qingnan Fan, Baoquan Chen, Hao Su, Leonidas J. Guibas
For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories.
1 code implementation • CVPR 2021 • Siyan Dong, Qingnan Fan, He Wang, Ji Shi, Li Yi, Thomas Funkhouser, Baoquan Chen, Leonidas Guibas
Localizing the camera in a known indoor environment is a key building block for scene mapping, robot navigation, AR, etc.
1 code implementation • 8 Dec 2020 • Qihang Fang, Yingda Yin, Qingnan Fan, Fei Xia, Siyan Dong, Sheng Wang, Jue Wang, Leonidas Guibas, Baoquan Chen
These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale.
1 code implementation • 7 Sep 2020 • Rongzheng Bian, Yumeng Xue, Liang Zhou, Jian Zhang, Baoquan Chen, Daniel Weiskopf, Yunhai Wang
We propose a visualization method to understand the effect of multidimensional projection on local subspaces, using implicit function differentiation.
1 code implementation • 22 Jun 2020 • Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu
Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.
no code implementations • 22 Jun 2020 • Mingyi Shi, Kfir Aberman, Andreas Aristidou, Taku Komura, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
no code implementations • 18 Jun 2020 • Xuelin Chen, Daniel Cohen-Or, Baoquan Chen, Niloy J. Mitra
NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation.
3 code implementations • NeurIPS 2020 • Jialei Huang, Guanqi Zhan, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong
Analogous to buying an IKEA furniture, given a set of 3D parts that can assemble a single shape, an intelligent agent needs to perceive the 3D part geometry, reason to propose pose estimations for the input parts, and finally call robotic planning and control routines for actuation.
1 code implementation • 12 May 2020 • Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring motion styles not observed during training.
1 code implementation • 12 May 2020 • Kfir Aberman, Peizhuo Li, Dani Lischinski, Olga Sorkine-Hornung, Daniel Cohen-Or, Baoquan Chen
In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons.
no code implementations • 26 Apr 2020 • Qi She, Fan Feng, Qi Liu, Rosa H. M. Chan, Xinyue Hao, Chuanlin Lan, Qihan Yang, Vincenzo Lomonaco, German I. Parisi, Heechul Bae, Eoin Brophy, Baoquan Chen, Gabriele Graffieti, Vidit Goel, Hyonyoung Han, Sathursan Kanagarajah, Somesh Kumar, Siew-Kei Lam, Tin Lun Lam, Liang Ma, Davide Maltoni, Lorenzo Pellegrini, Duvindu Piyasena, ShiLiang Pu, Debdoot Sheet, Soonyong Song, Youngsung Son, Zhengwei Wang, Tomas E. Ward, Jianwen Wu, Meiqing Wu, Di Xie, Yangsheng Xu, Lin Yang, Qiaoyong Zhong, Liguang Zhou
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams).
1 code implementation • ECCV 2020 • Rundi Wu, Xuelin Chen, Yixin Zhuang, Baoquan Chen
Several deep learning methods have been proposed for completing partial data from shape acquisition setups, i. e., filling the regions that were missing in the shape.
no code implementations • 8 Dec 2019 • Yingda Yin, Qingnan Fan, Dong-Dong Chen, Yujie Wang, Angelica Aviles-Rivero, Ruoteng Li, Carola-Bibiane Schnlieb, Dani Lischinski, Baoquan Chen
Reflections are very common phenomena in our daily photography, which distract people's attention from the scene behind the glass.
1 code implementation • 28 Nov 2019 • Rong Zhang, Wei Li, Peng Wang, Chenye Guan, Jin Fang, Yuhang Song, Jinhui Yu, Baoquan Chen, Weiwei Xu, Ruigang Yang
To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically.
no code implementations • 26 Nov 2019 • Siyan Dong, Songyin Wu, Yixin Zhuang, Kai Xu, Shanghang Zhang, Baoquan Chen
To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately.
2 code implementations • CVPR 2020 • Rundi Wu, Yixin Zhuang, Kai Xu, Hao Zhang, Baoquan Chen
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly.
1 code implementation • 22 Nov 2019 • Guanqi Zhan, Yihao Zhao, Bingchan Zhao, Haoqi Yuan, Baoquan Chen, Hao Dong
By mapping the discrete label-specific attribute features into a continuous prior distribution, we leverage the advantages of both discrete labels and reference images to achieve image manipulation in a hybrid fashion.
no code implementations • 11 Jul 2019 • Qingnan Fan, Dong-Dong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen
To overcome this limitation, we propose a new decoupled learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network.
2 code implementations • 5 May 2019 • Kfir Aberman, Rundi Wu, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view.
2 code implementations • ICLR 2020 • Xuelin Chen, Baoquan Chen, Niloy J. Mitra
As 3D scanning solutions become increasingly popular, several deep learning setups have been developed geared towards that task of scan completion, i. e., plausibly filling in regions there were missed in the raw scans.
1 code implementation • NeurIPS 2018 • Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen
We present a simple and general framework for feature learning from point cloud.
Ranked #5 on 3D Semantic Segmentation on DALES
no code implementations • 22 Nov 2018 • Peng Jiang, Zhiyi Pan, Nuno Vasconcelos, Baoquan Chen, Jingliang Peng
Following this analysis, we propose super diffusion, a novel inclusive learning-based framework for salient object detection, which makes the optimum and robust performance by integrating a large pool of feature spaces, scales and even features originally computed for non-diffusion-based salient object detection.
1 code implementation • 7 Nov 2018 • Qingnan Fan, Jiaolong Yang, David Wipf, Baoquan Chen, Xin Tong
Image smoothing represents a fundamental component of many disparate computer vision and graphics applications.
no code implementations • 21 Aug 2018 • Kfir Aberman, Mingyi Shi, Jing Liao, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances.
no code implementations • 15 Aug 2018 • Bin Wang, Paul Kry, Yuanmin Deng, Uri Ascher, Hui Huang, Baoquan Chen
The challenge is that such data is sparse as it is consistently given only on part of the surface.
2 code implementations • ECCV 2018 • Changqing Zou, Qian Yu, Ruofei Du, Haoran Mo, Yi-Zhe Song, Tao Xiang, Chengying Gao, Baoquan Chen, Hao Zhang
We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level.
no code implementations • 24 Jul 2018 • Manyi Li, Akshay Gadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, Hao Zhang
We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently.
1 code implementation • ECCV 2018 • Qingnan Fan, Dong-Dong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen
Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising.
no code implementations • NeurIPS 2018 • Peng Jiang, Fanglin Gu, Yunhai Wang, Changhe Tu, Baoquan Chen
Deep Neural Networks (DNNs) have recently shown state of the art performance on semantic segmentation tasks, however, they still suffer from problems of poor boundary localization and spatial fragmented predictions.
2 code implementations • 10 May 2018 • Kfir Aberman, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications.
14 code implementations • NeurIPS 2018 • Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)
no code implementations • 22 Nov 2017 • Zhenhua Wang, Fanglin Gu, Dani Lischinski, Daniel Cohen-Or, Changhe Tu, Baoquan Chen
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation.
1 code implementation • ICCV 2017 • Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf
This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering.
no code implementations • 29 Mar 2017 • Qiong Zeng, Baoquan Chen, Yanir Kleiman, Daniel Cohen-Or, Yangyan Li
Understanding semantic similarity among images is the core of a wide range of computer vision applications.
no code implementations • CVPR 2018 • Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem.
no code implementations • 18 Aug 2016 • Huayong Xu, Yangyan Li, Wenzheng Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.
no code implementations • 10 Apr 2016 • Wenzheng Chen, Huan Wang, Yangyan Li, Hao Su, Zhenhua Wang, Changhe Tu, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
Human 3D pose estimation from a single image is a challenging task with numerous applications.