Search Results for author: Chunxia Xiao

Found 22 papers, 11 papers with code

DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos

no code implementations19 Dec 2023 Chunjie Luo, Fei Luo, Yusen Wang, Enxu Zhao, Chunxia Xiao

To model the deformation more accurately, we propose to initialize an estimated 3D clothed human in the canonical space, as it is easier for deformation fields to learn from the clothed human than from SMPL.

NeTO:Neural Reconstruction of Transparent Objects with Self-Occlusion Aware Refraction-Tracing

no code implementations ICCV 2023 Zongcheng Li, Xiaoxiao Long, Yusen Wang, Tuo Cao, Wenping Wang, Fei Luo, Chunxia Xiao

In this paper, we propose to leverage implicit Signed Distance Function (SDF) as surface representation, and optimize the SDF field via volume rendering with a self-occlusion aware refractive ray tracing.

Transparent objects

Learning Long-Range Information with Dual-Scale Transformers for Indoor Scene Completion

no code implementations ICCV 2023 Ziqi Wang, Fei Luo, Xiaoxiao Long, Wenxiao Zhang, Chunxia Xiao

Due to the limited resolution of 3D sensors and the inevitable mutual occlusion between objects, 3D scans of real scenes are commonly incomplete.

Document Image Shadow Removal Guided by Color-Aware Background

1 code implementation CVPR 2023 Ling Zhang, Yinghao He, Qing Zhang, Zheng Liu, Xiaolong Zhang, Chunxia Xiao

In this paper, we present a color-aware background extraction network (CBENet) for extracting a spatially varying background image that accurately depicts the background colors of the document.

Document Shadow Removal Image Shadow Removal

NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction

no code implementations13 Oct 2022 Yusen Wang, Zongcheng Li, Yu Jiang, Kaixuan Zhou, Tuo Cao, Yanping Fu, Chunxia Xiao

Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity.

Indoor Scene Reconstruction Surface Reconstruction

Luminance Attentive Networks for HDR Image and Panorama Reconstruction

1 code implementation14 Sep 2021 Hanning Yu, Wentao Liu, Chengjiang Long, Bo Dong, Qin Zou, Chunxia Xiao

Based on this observation, we propose a novel normalization method called " HDR calibration " for HDR images stored in relative luminance, calibrating HDR images into a similar luminance scale according to the LDR images.

HDR Reconstruction inverse tone mapping +2

CANet: A Context-Aware Network for Shadow Removal

1 code implementation ICCV 2021 Zipei Chen, Chengjiang Long, Ling Zhang, Chunxia Xiao

In this paper, we propose a novel two-stage context-aware network named CANet for shadow removal, in which the contextual information from non-shadow regions is transferred to shadow regions at the embedded feature spaces.

Patch Matching Shadow Removal

Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning

1 code implementation5 Aug 2021 Xinzhi Dong, Chengjiang Long, Wenju Xu, Chunxia Xiao

With the well-designed Dual-GCN, we can make the linguistic transformer better understand the relationship between different objects in a single image and make full use of similar images as auxiliary information to generate a reasonable caption description for a single image.

Image Captioning Object

Deep Image-based Illumination Harmonization

no code implementations CVPR 2022 Zhongyun Bao, Chengjiang Long, Gang Fu, Daquan Liu, Yuanzhen Li, Jiaming Wu, Chunxia Xiao

Specifically, we firstly apply a physically-based rendering method to construct a large-scale, high-quality dataset (named IH) for our task, which contains various types of foreground objects and background scenes with different lighting conditions.


CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation

no code implementations28 Jul 2021 Tao Hu, Chengjiang Long, Chunxia Xiao

Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize $K$ photo-realistic images simultaneously.

Text-to-Image Generation

Detail Preserved Point Cloud Completion via Separated Feature Aggregation

1 code implementation ECCV 2020 Wenxiao Zhang, Qingan Yan, Chunxia Xiao

In this work, instead of using a global feature to recover the whole complete surface, we explore the functionality of multi-level features and aggregate different features to represent the known part and the missing part separately.

Point Cloud Completion

VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling

no code implementations26 Jul 2019 Tao Hu, Chengjiang Long, Leheng Zhang, Chunxia Xiao

In this paper, we propose a novel way to interpret text information by extracting visual feature presentation from multiple high-resolution and photo-realistic synthetic images generated by Text-to-image Generative Adversarial Network (GAN) to improve the performance of image labeling.

Generative Adversarial Network

Enhancing Underexposed Photos using Perceptually Bidirectional Similarity

no code implementations25 Jul 2019 Qing Zhang, Yongwei Nie, Lei Zhu, Chunxia Xiao, Wei-Shi Zheng

To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.

Video Enhancement

Distinguishing the Indistinguishable: Exploring Structural Ambiguities via Geodesic Context

1 code implementation CVPR 2017 Qingan Yan, Long Yang, Ling Zhang, Chunxia Xiao

A perennial problem in structure from motion (SfM) is visual ambiguity posed by repetitive structures.

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