Search Results for author: Nan Xue

Found 46 papers, 25 papers with code

Rectified Diffusion Guidance for Conditional Generation

no code implementations24 Oct 2024 Mengfei Xia, Nan Xue, Yujun Shen, Ran Yi, Tieliang Gong, Yong-Jin Liu

Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion model sampling.

Denoising

Partial Distribution Matching via Partial Wasserstein Adversarial Networks

no code implementations16 Sep 2024 Zi-Ming Wang, Nan Xue, Ling Lei, Rebecka Jörnsten, Gui-Song Xia

This paper studies the problem of distribution matching (DM), which is a fundamental machine learning problem seeking to robustly align two probability distributions.

Partial Domain Adaptation

A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction

no code implementations30 May 2024 Jianghao Shen, Nan Xue, Tianfu Wu

Child 3D Gaussians are learned via a lightweight Multi-Layer Perceptron (MLP) which takes as input the projected image features of a parent 3D Gaussian and the embedding of a target camera view.

3D Reconstruction Novel View Synthesis +1

Stratified Avatar Generation from Sparse Observations

no code implementations CVPR 2024 Han Feng, Wenchao Ma, Quankai Gao, Xianwei Zheng, Nan Xue, Huijuan Xu

This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the head and hands.

Decoder

Multi-View Attentive Contextualization for Multi-View 3D Object Detection

no code implementations CVPR 2024 Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu

We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection.

3D Object Detection Object +1

WDMoE: Wireless Distributed Large Language Models with Mixture of Experts

no code implementations6 May 2024 Nan Xue, Yaping Sun, Zhiyong Chen, Meixia Tao, Xiaodong Xu, Liang Qian, Shuguang Cui, Ping Zhang

In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, deploying LLMs collaboratively across edge servers of base station (BS) and mobile devices in the wireless communications system.

MaPa: Text-driven Photorealistic Material Painting for 3D Shapes

no code implementations26 Apr 2024 Shangzhan Zhang, Sida Peng, Tao Xu, Yuanbo Yang, Tianrun Chen, Nan Xue, Yujun Shen, Hujun Bao, Ruizhen Hu, Xiaowei Zhou

Instead of relying on extensive paired data, i. e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs.

Bridging 3D Gaussian and Mesh for Freeview Video Rendering

no code implementations18 Mar 2024 Yuting Xiao, Xuan Wang, Jiafei Li, Hongrui Cai, Yanbo Fan, Nan Xue, Minghui Yang, Yujun Shen, Shenghua Gao

To this end, we propose a novel approach, GauMesh, to bridge the 3D Gaussian and Mesh for modeling and rendering the dynamic scenes.

Novel View Synthesis

Cross-level Attention with Overlapped Windows for Camouflaged Object Detection

no code implementations28 Nov 2023 Jiepan Li, Fangxiao Lu, Nan Xue, Zhuohong Li, Hongyan zhang, wei he

In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features.

object-detection Object Detection

Patched Line Segment Learning for Vector Road Mapping

no code implementations6 Sep 2023 Jiakun Xu, Bowen Xu, Gui-Song Xia, Liang Dong, Nan Xue

In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture.

NEAT: Distilling 3D Wireframes from Neural Attraction Fields

1 code implementation CVPR 2024 Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu, Yujun Shen

Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions.

3D Wireframe Reconstruction Novel View Synthesis

Depth and DOF Cues Make A Better Defocus Blur Detector

1 code implementation20 Jun 2023 Yuxin Jin, Ming Qian, Jincheng Xiong, Nan Xue, Gui-Song Xia

Our method proposes a depth feature distillation strategy to obtain depth knowledge from a pre-trained monocular depth estimation model and uses a DOF-edge loss to understand the relationship between DOF and depth.

Defocus Blur Detection Monocular Depth Estimation

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

1 code implementation CVPR 2023 Jian Ding, Nan Xue, Gui-Song Xia, Bernt Schiele, Dengxin Dai

This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain.

Domain Generalization Segmentation +1

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

no code implementations ICCV 2023 Xianpeng Liu, Ce Zheng, Kelvin Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu

Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner.

Denoising Monocular 3D Object Detection +1

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

1 code implementation30 Nov 2022 Bin Tan, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.

3D Reconstruction Camera Pose Estimation +1

Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces

1 code implementation CVPR 2023 Yuxi Xiao, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.

3D Reconstruction Camera Pose Estimation +2

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

1 code implementation24 Oct 2022 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions.

Self-Supervised Learning Wireframe Parsing

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

1 code implementation15 Aug 2022 Wenchao Ma, Bin Tan, Nan Xue, Tianfu Wu, Xianwei Zheng, Gui-Song Xia

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.

Accurate Polygonal Mapping of Buildings in Satellite Imagery

1 code implementation1 Aug 2022 Bowen Xu, Jiakun Xu, Nan Xue, Gui-Song Xia

We addressed such an issue by exploiting the hierarchical supervision (of bottom-level vertices, mid-level line segments and the high-level regional masks) and proposed a novel interaction mechanism of feature embedding sourced from different levels of supervision signals to obtain reversible building masks for polygonal mapping of buildings.

Revisiting Document Image Dewarping by Grid Regularization

no code implementations CVPR 2022 Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia

This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization.

Local Distortion Optical Flow Estimation

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

no code implementations ICLR 2022 Zi-Ming Wang, Nan Xue, Ling Lei, Gui-Song Xia

To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy.

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

2 code implementations9 Dec 2021 Xianpeng Liu, Nan Xue, Tianfu Wu

It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection.

Monocular 3D Object Detection Object +2

Parsing Table Structures in the Wild

2 code implementations ICCV 2021 Rujiao Long, Wen Wang, Nan Xue, Feiyu Gao, Zhibo Yang, Yongpan Wang, Gui-Song Xia

In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions.

Object Detection

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

no code implementations ICCV 2021 Bin Tan, Nan Xue, Song Bai, Tianfu Wu, Gui-Song Xia

This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.

Decoder

ReDet: A Rotation-equivariant Detector for Aerial Object Detection

4 code implementations CVPR 2021 Jiaming Han, Jian Ding, Nan Xue, Gui-Song Xia

More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size.

Ranked #19 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +1

Deep Graph Matching under Quadratic Constraint

1 code implementation CVPR 2021 Quankai Gao, Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia

Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes.

Descriptive Graph Matching

Unmixing Convolutional Features for Crisp Edge Detection

1 code implementation19 Nov 2020 Linxi Huan, Nan Xue, Xianwei Zheng, wei he, Jianya Gong, Gui-Song Xia

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.

Edge Classification Edge Detection

Zero-Assignment Constraint for Graph Matching with Outliers

1 code implementation CVPR 2020 Fu-Dong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia

Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications.

Graph Matching valid

Fisheye Distortion Rectification from Deep Straight Lines

no code implementations25 Mar 2020 Zhu-Cun Xue, Nan Xue, Gui-Song Xia

This paper presents a novel line-aware rectification network (LaRecNet) to address the problem of fisheye distortion rectification based on the classical observation that straight lines in 3D space should be still straight in image planes.

SSIM

Holistically-Attracted Wireframe Parsing

1 code implementation CVPR 2020 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.

Line Segment Detection Wireframe Parsing

Learning Regional Attraction for Line Segment Detection

no code implementations18 Dec 2019 Nan Xue, Song Bai, Fu-Dong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang, Philip H. S. Torr

Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.

Line Segment Detection

Learning to Calibrate Straight Lines for Fisheye Image Rectification

no code implementations CVPR 2019 Zhu-Cun Xue, Nan Xue, Gui-Song Xia, Weiming Shen

This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images.

A Functional Representation for Graph Matching

1 code implementation16 Jan 2019 Fu-Dong Wang, Gui-Song Xia, Nan Xue, Yi-Peng Zhang, Marcello Pelillo

In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms.

Graph Matching

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

1 code implementation1 Dec 2018 Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, Qikai Lu

Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects.

Ranked #50 on Object Detection In Aerial Images on DOTA (using extra training data)

General Classification Object +4

GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images

no code implementations7 Nov 2018 Gui-Song Xia, Jin Huang, Nan Xue, Qikai Lu, Xiaoxiang Zhu

More precisely, given an image, the geometric saliency is derived from a mid-level geometric representations based on meaningful junctions that can locally describe geometrical structures of images.

Extracting Buildings In Remote Sensing Images

Adaptively Transforming Graph Matching

no code implementations ECCV 2018 Fu-Dong Wang, Nan Xue, Yi-Peng Zhang, Xiang Bai, Gui-Song Xia

Due to an efficient Frank-Wolfe method-based optimization strategy, we can handle graphs with hundreds and thousands of nodes within an acceptable amount of time.

Domain Adaptation Graph Matching

Anisotropic-Scale Junction Detection and Matching for Indoor Images

no code implementations16 Mar 2017 Nan Xue, Gui-Song Xia, Xiang Bai, Liangpei Zhang, Weiming Shen

This paper presents a novel approach to junction detection and characterization that exploits the locally anisotropic geometries of a junction and estimates the scales of these geometries using an \emph{a contrario} model.

Junction Detection

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