b'Li Niu'

research

∙ 08/19/2023

ControlCom: Controllable Image Composition using Diffusion Model

Image composition targets at synthesizing a realistic composite image fr...

0 Bo Zhang, et al. ∙

research

∙ 08/19/2023

DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation

Image composition refers to inserting a foreground object into a backgro...

0 Qingyang Liu, et al. ∙

research

∙ 08/09/2023

Foreground Object Search by Distilling Composite Image Feature

Foreground object search (FOS) aims to find compatible foreground object...

0 Bo Zhang, et al. ∙

research

∙ 08/05/2023

Deep Image Harmonization in Dual Color Spaces

Image harmonization is an essential step in image composition that adjus...

0 Linfeng Tan, et al. ∙

research

∙ 08/04/2023

Painterly Image Harmonization using Diffusion Model

Painterly image harmonization aims to insert photographic objects into p...

0 Lingxiao Lu, et al. ∙

research

∙ 08/04/2023

Scene-aware Human Pose Generation using Transformer

Affordance learning considers the interaction opportunities for an actor...

0 Jieteng Yao, et al. ∙

research

∙ 08/01/2023

Deep Image Harmonization with Learnable Augmentation

The goal of image harmonization is adjusting the foreground appearance i...

0 Li Niu, et al. ∙

research

∙ 08/01/2023

Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation

Given a composite image, image harmonization aims to adjust the foregrou...

0 Li Niu, et al. ∙

research

∙ 06/30/2023

RdSOBA: Rendered Shadow-Object Association Dataset

Image composition refers to inserting a foreground object into a backgro...

0 Xinhao Tao, et al. ∙

research

∙ 05/11/2023

WeditGAN: Few-shot Image Generation via Latent Space Relocation

In few-shot image generation, directly training GAN models on just a han...

0 Yuxuan Duan, et al. ∙

research

∙ 03/04/2023

Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation

The performances of defect inspection have been severely hindered by ins...

0 Yuxuan Duan, et al. ∙

research

∙ 12/17/2022

Painterly Image Harmonization in Dual Domains

Image harmonization aims to produce visually harmonious composite images...

0 Junyan Cao, et al. ∙

research

∙ 12/06/2022

Video Object of Interest Segmentation

In this work, we present a new computer vision task named video object o...

0 Siyuan Zhou, et al. ∙

research

∙ 10/05/2022

Weak-shot Semantic Segmentation via Dual Similarity Transfer

Semantic segmentation is an important and prevalent task, but severely s...

11 Junjie Chen, et al. ∙

research

∙ 10/05/2022

Inharmonious Region Localization via Recurrent Self-Reasoning

Synthetic images created by image editing operations are prevalent, but ...

0 Penghao Wu, et al. ∙

research

∙ 10/05/2022

Inharmonious Region Localization with Auxiliary Style Feature

With the prevalence of image editing techniques, users can create fantas...

0 Penghao Wu, et al. ∙

research

∙ 09/30/2022

Inharmonious Region Localization by Magnifying Domain Discrepancy

Inharmonious region localization aims to localize the region in a synthe...

0 Jing Liang, et al. ∙

research

∙ 07/23/2022

Learning Object Placement via Dual-path Graph Completion

Object placement aims to place a foreground object over a background ima...

0 Siyuan Zhou, et al. ∙

research

∙ 07/22/2022

Few-shot Image Generation Using Discrete Content Representation

Few-shot image generation and few-shot image translation are two related...

0 Yan Hong, et al. ∙

research

∙ 07/21/2022

Human-centric Image Cropping with Partition-aware and Content-preserving Features

Image cropping aims to find visually appealing crops in an image, which ...

0 Bo Zhang, et al. ∙

research

∙ 07/06/2022

Spatial Transformation for Image Composition via Correspondence Learning

When using cut-and-paste to acquire a composite image, the geometry inco...

0 Bo Zhang, et al. ∙

research

∙ 06/01/2022

CcHarmony: Color-checker based Image Harmonization Dataset

Image harmonization targets at adjusting the foreground in a composite i...

0 Haoxu Huang, et al. ∙

research

∙ 05/30/2022

From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

Video understanding has achieved great success in representation learnin...

0 Jiangtong Li, et al. ∙

research

∙ 05/28/2022

Fast Object Placement Assessment

Object placement assessment (OPA) aims to predict the rationality score ...

0 Li Niu, et al. ∙

research

∙ 05/02/2022

Deep Video Harmonization with Color Mapping Consistency

Video harmonization aims to adjust the foreground of a composite video t...

21 Xinyuan Lu, et al. ∙

research

∙ 10/27/2021

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

Object detection has achieved promising success, but requires large-scal...

8 Yan Liu, et al. ∙

research

∙ 10/06/2021

Weak Novel Categories without Tears: A Survey on Weak-Shot Learning

Deep learning is a data-hungry approach, which requires massive training...

0 Li Niu, et al. ∙

research

∙ 10/04/2021

Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary

Weakly-supervised semantic segmentation (WSSS) with image-level labels h...

0 Siyuan Zhou, et al. ∙

research

∙ 09/18/2021

HYouTube: Video Harmonization Dataset

Video composition aims to generate a composite video by combining the fo...

0 Xinyuan Lu, et al. ∙

research

∙ 09/14/2021

High-Resolution Image Harmonization via Collaborative Dual Transformations

Given a composite image, image harmonization aims to adjust the foregrou...

0 Wenyan Cong, et al. ∙

research

∙ 08/08/2021

Visible Watermark Removal via Self-calibrated Localization and Background Refinement

Superimposing visible watermarks on images provides a powerful weapon to...

2 Jing Liang, et al. ∙

research

∙ 07/05/2021

OPA: Object Placement Assessment Dataset

Image composition aims to generate realistic composite image by insertin...

0 Liu Liu, et al. ∙

research

∙ 06/28/2021

Making Images Real Again: A Comprehensive Survey on Deep Image Composition

As a common image editing operation, image composition aims to cut the f...

0 Li Niu, et al. ∙

research

∙ 05/23/2021

End-to-End Video Object Detection with Spatial-Temporal Transformers

Recently, DETR and Deformable DETR have been proposed to eliminate the n...

29 Lu He, et al. ∙

research

∙ 04/21/2021

Shadow Generation for Composite Image in Real-world Scenes

Image composition targets at inserting a foreground object on a backgrou...

0 Yan Hong, et al. ∙

research

∙ 04/19/2021

Inharmonious Region Localization

The advance of image editing techniques allows users to create artistic ...

0 Jing Liang, et al. ∙

research

∙ 04/07/2021

Image Composition Assessment with Saliency-augmented Multi-pattern Pooling

Image composition assessment is crucial in aesthetic assessment, which a...

2 Bo Zhang, et al. ∙

research

∙ 03/31/2021

Deep Image Harmonization by Bridging the Reality Gap

Image harmonization has been significantly advanced with large-scale har...

0 Wenyan Cong, et al. ∙

research

∙ 12/14/2020

Disentangled Information Bottleneck

The information bottleneck (IB) method is a technique for extracting inf...

0 Ziqi Pan, et al. ∙

research

∙ 09/25/2020

From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation

Zero-shot learning has been actively studied for image classification ta...

10 Zhangxuan Gu, et al. ∙

research

∙ 09/19/2020

Weak-shot Fine-grained Classification via Similarity Transfer

Recognizing fine-grained categories remains a challenging task, due to t...

0 Junjie Chen, et al. ∙

research

∙ 09/19/2020

BargainNet: Background-Guided Domain Translation for Image Harmonization

Image composition is a fundamental operation in image editing field. How...

3 Wenyan Cong, et al. ∙

research

∙ 09/18/2020

DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta

Learning to generate new images for a novel category based on only a few...

29 Yan Hong, et al. ∙

research

∙ 08/16/2020

Context-aware Feature Generation for Zero-shot Semantic Segmentation

Existing semantic segmentation models heavily rely on dense pixel-wise a...

0 Zhangxuan Gu, et al. ∙

research

∙ 08/05/2020

F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation

In order to generate images for a given category, existing deep generati...

5 Yan Hong, et al. ∙

research

∙ 03/15/2020

Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets

Multi-task Learning (MTL) for classification with disjoint datasets aims...

13 Yan Hong, et al. ∙

research

∙ 03/07/2020

MatchingGAN: Matching-based Few-shot Image Generation

To generate new images for a given category, most deep generative models...

11 Yan Hong, et al. ∙

research

∙ 12/01/2019

Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition

Static image action recognition, which aims to recognize action based on...

0 Yiyi Zhang, et al. ∙

research

∙ 11/29/2019

Bi-Directional Domain Translation for Zero-Shot Sketch-Based Image Retrieval

The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketc...

0 Jiangtong Li, et al. ∙

research

∙ 11/27/2019

Deep Image Harmonization via Domain Verification

Image composition is an important operation in image processing, but the...

5 Wenyan Cong, et al. ∙

Li Niu

Featured Co-authors