Search Results for author: Baoquan Chen

Found 69 papers, 33 papers with code

GFPack++: Improving 2D Irregular Packing by Learning Gradient Field with Attention

no code implementations9 Jun 2024 Tianyang Xue, Lin Lu, Yang Liu, Mingdong Wu, Hao Dong, Yanbin Zhang, Renmin Han, Baoquan Chen

The difficulty of learning from teacher packing is to capture the complex geometric relationships among packing examples, which include the spatial (position, orientation) relationships of objects, their geometric features, and container boundary conditions.

Combinatorial Optimization

DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Refocusing,Defocus Rendering and Blur Removal

no code implementations27 May 2024 Yujie Wang, PRANEETH CHAKRAVARTHULA, Baoquan Chen

It also enables rendering varying DOF effects of 3D scenes post-optimization, and generating AiF images from defocused training images.

3D Scene Reconstruction Novel View Synthesis

Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis

1 code implementation16 May 2024 Zeyi Zhang, Tenglong Ao, Yuyao Zhang, Qingzhe Gao, Chuan Lin, Baoquan Chen, Libin Liu

In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence.

Language Modelling Large Language Model +1

MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization

no code implementations10 May 2024 Pengcheng Zhu, Yaoming Zhuang, Baoquan Chen, Li Li, Chengdong Wu, Zhanlin Liu

To address these limitations, we uniquely integrates advanced sparse visual odometry with a dense Gaussian Splatting scene representation for the first time, thereby eliminating the dependency on depth maps typical of Gaussian Splatting-based SLAM systems and enhancing tracking robustness.

Depth Estimation Novel View Synthesis +3

BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors

no code implementations18 Mar 2024 Tingyang Zhang, Qingzhe Gao, Weiyu Li, Libin Liu, Baoquan Chen

In this work, we propose a method to build animatable 3D Gaussian Splatting from monocular video with diffusion priors.

3D Reconstruction

SAI3D: Segment Any Instance in 3D Scenes

no code implementations CVPR 2024 Yingda Yin, Yuzheng Liu, Yang Xiao, Daniel Cohen-Or, Jingwei Huang, Baoquan Chen

Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories.

3D Instance Segmentation Scene Parsing +2

Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning

1 code implementation1 Dec 2023 Kangcheng Liu, Yong-Jin Liu, Kai Tang, Ming Liu, Baoquan Chen

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels.

Contrastive Learning Few-Shot Learning +2

Learning Gradient Fields for Scalable and Generalizable Irregular Packing

no code implementations18 Oct 2023 Tianyang Xue, Mingdong Wu, Lin Lu, Haoxuan Wang, Hao Dong, Baoquan Chen

In this work, we delve deeper into a novel machine learning-based approach that formulates the packing problem as conditional generative modeling.

Collision Avoidance Layout Design +1

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

no code implementations16 Oct 2023 Heyuan Yao, Zhenhua Song, Yuyang Zhou, Tenglong Ao, Baoquan Chen, Libin Liu

In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations.

In-Context Learning Model-based Reinforcement Learning

Lazy Visual Localization via Motion Averaging

no code implementations19 Jul 2023 Siyan Dong, Shaohui Liu, Hengkai Guo, Baoquan Chen, Marc Pollefeys

Visual (re)localization is critical for various applications in computer vision and robotics.

Visual Localization

Example-based Motion Synthesis via Generative Motion Matching

1 code implementation1 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.

Motion Synthesis

Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution

no code implementations17 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.


Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images

no code implementations13 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.

3D-Aware Image Synthesis

Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling

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.

Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast

1 code implementation CVPR 2023 Kangcheng Liu, Xinhu Zheng, Chaoqun Wang, Kai Tang, Ming Liu, Baoquan Chen

The second is that we prevent over-discrimination between 3D segments/objects and encourage grouped foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively.

3D Semantic Segmentation Contrastive Learning +8

A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation

no code implementations3 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.


ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters

no code implementations12 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.

Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors

no code implementations25 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.


Visual Localization via Few-Shot Scene Region Classification

1 code implementation14 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.

General Classification Memorization +2

Multi-Robot Active Mapping via Neural Bipartite Graph Matching

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.

Graph Matching Graph Neural Network +3

FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering

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.

Pseudo Label Pseudo Label Filtering +1

Self-Conditioned Generative Adversarial Networks for Image Editing

1 code implementation8 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.


Unsupervised Co-part Segmentation through Assembly

1 code implementation10 Jun 2021 Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen

Co-part segmentation is an important problem in computer vision for its rich applications.


MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras

no code implementations8 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.

Neural Implicit 3D Shapes from Single Images with Spatial Patterns

1 code implementation6 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.

3D Reconstruction 3D Shape Reconstruction +1

Learning Skeletal Articulations with Neural Blend Shapes

1 code implementation6 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.

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

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.

Pose Tracking

Towards Accurate Active Camera Localization

1 code implementation8 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.

Camera Localization Camera Pose Estimation +2

Implicit Multidimensional Projection of Local Subspaces

1 code implementation7 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.

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency

no code implementations22 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.

DO-Conv: Depthwise Over-parameterized Convolutional Layer

1 code implementation22 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.

Image Classification

Towards a Neural Graphics Pipeline for Controllable Image Generation

no code implementations18 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.

Image Generation Neural Rendering

Generative 3D Part Assembly via Dynamic Graph Learning

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.

Graph Learning Graph Neural Network +2

Unpaired Motion Style Transfer from Video to Animation

1 code implementation12 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.

3D Reconstruction Motion Style Transfer +1

Skeleton-Aware Networks for Deep Motion Retargeting

1 code implementation12 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.

motion retargeting Motion Synthesis

Multimodal Shape Completion via Conditional Generative Adversarial Networks

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.


Single image reflection removal via learning with multi-image constraints

no code implementations8 Dec 2019 Yingda Yin, Qingnan Fan, Dong-Dong Chen, Yujie Wang, Angelica Aviles-Rivero, Ruoteng Li, Carola-Bibiane Schnlieb, Baoquan Chen

Reflections are very common phenomena in our daily photography, which distract people's attention from the scene behind the glass.

Reflection Removal

AutoRemover: Automatic Object Removal for Autonomous Driving Videos

1 code implementation28 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.

Autonomous Driving Object +1

Decoupling Features and Coordinates for Few-shot RGB Relocalization

no code implementations26 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.

Camera Relocalization Pose Estimation +1

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

3 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.

3D Reconstruction Decoder +1

DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation

1 code implementation22 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.

Attribute Image Manipulation +1

A General Decoupled Learning Framework for Parameterized Image Operators

no code implementations11 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.

Learning Character-Agnostic Motion for Motion Retargeting in 2D

2 code implementations5 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.

3D Reconstruction motion retargeting +2

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

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.

Point Cloud Completion

Super Diffusion for Salient Object Detection

no code implementations22 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.

Clustering Object +3

Image Smoothing via Unsupervised Learning

1 code implementation7 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.

Image Manipulation image smoothing

Deep Video-Based Performance Cloning

no code implementations21 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.

Neural Material: Learning Elastic Constitutive Material and Damping Models from Sparse Data

no code implementations15 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.


SketchyScene: Richly-Annotated Scene Sketches

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.

Colorization Image Retrieval +3

GRAINS: Generative Recursive Autoencoders for INdoor Scenes

no code implementations24 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.


Decouple Learning for Parameterized Image Operators

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.

Denoising image smoothing +1

DifNet: Semantic Segmentation by Diffusion Networks

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.

Segmentation Semantic Segmentation

Neural Best-Buddies: Sparse Cross-Domain Correspondence

2 code implementations10 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.

Image Morphing

PointCNN: Convolution On $\mathcal{X}$-Transformed Points

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)

3D Instance Segmentation 3D Part Segmentation +1

Neuron-level Selective Context Aggregation for Scene Segmentation

no code implementations22 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.

Scene Segmentation Segmentation

A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

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.

image smoothing Reflection Removal +1

Bundle Optimization for Multi-aspect Embedding

no code implementations29 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.

Clustering Image Classification +2

Revisiting Deep Intrinsic Image Decompositions

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.

A Holistic Approach for Data-Driven Object Cutout

no code implementations18 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.


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