110 citations · 454 across the 51 of their papers we have counts for
50 papers · 1 filter
Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles
Li Niu, Yan Hong, Junyan Cao +1
Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background. Different from previous auto-encoder based harmonization networks, we…
Painterly Image Harmonization by Learning from Painterly Objects
Li Niu, Junyan Cao, Yan Hong +1
Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the backgro…
Painterly Image Harmonization via Adversarial Residual Learning
Xudong Wang, Li Niu, Junyan Cao +2
Image compositing plays a vital role in photo editing. After inserting a foreground object into another background image, the composite image may look unnatural and inharmonious. W…
Virtual Accessory Try-On via Keypoint Hallucination
Junhong Gou, Bo Zhang, Li Niu +4
The virtual try-on task refers to fitting the clothes from one image onto another portrait image. In this paper, we focus on virtual accessory try-on, which fits accessory (e.g., g…
Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow
Junhong Gou, Siyu Sun, Jianfu Zhang +3
Virtual try-on is a critical image synthesis task that aims to transfer clothes from one image to another while preserving the details of both humans and clothes. While many existi…
Deep Image Harmonization in Dual Color Spaces
Linfeng Tan, Jiangtong Li, Li Niu +1
Image harmonization is an essential step in image composition that adjusts the appearance of composite foreground to address the inconsistency between foreground and background. Ex…
Painterly Image Harmonization using Diffusion Model
Lingxiao Lu, Jiangtong Li, Junyan Cao +2
Painterly image harmonization aims to insert photographic objects into paintings and obtain artistically coherent composite images. Previous methods for this task mainly rely on in…
Deep Image Harmonization with Learnable Augmentation
Li Niu, Junyan Cao, Wenyan Cong +1
The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datase…
Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation
Li Niu, Linfeng Tan, Xinhao Tao +4
Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground fea…
WeditGAN: Few-Shot Image Generation via Latent Space Relocation
Yuxuan Duan, Li Niu, Yan Hong +1
In few-shot image generation, directly training GAN models on just a handful of images faces the risk of overfitting. A popular solution is to transfer the models pretrained on lar…
Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation
Yuxuan Duan, Yan Hong, Li Niu +1
The performances of defect inspection have been severely hindered by insufficient defect images in industries, which can be alleviated by generating more samples as data augmentati…
Weak-shot Semantic Segmentation via Dual Similarity Transfer
Junjie Chen, Li Niu, Siyuan Zhou +3
Semantic segmentation is an important and prevalent task, but severely suffers from the high cost of pixel-level annotations when extending to more classes in wider applications. T…
Inharmonious Region Localization via Recurrent Self-Reasoning
Penghao Wu, Li Niu, Jing Liang +1
Synthetic images created by image editing operations are prevalent, but the color or illumination inconsistency between the manipulated region and background may make it unrealisti…
Inharmonious Region Localization with Auxiliary Style Feature
Penghao Wu, Li Niu, Liqing Zhang
With the prevalence of image editing techniques, users can create fantastic synthetic images, but the image quality may be compromised by the color/illumination discrepancy between…
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
Yan Hong, Li Niu, Jianfu Zhang +1
Learning to generate new images for a novel category based on only a few images, named as few-shot image generation, has attracted increasing research interest. Several state-of-th…
Learning Object Placement via Dual-path Graph Completion
Siyuan Zhou, Liu Liu, Li Niu +1
Object placement aims to place a foreground object over a background image with a suitable location and size. In this work, we treat object placement as a graph completion problem…
Few-shot Image Generation Using Discrete Content Representation
Yan Hong, Li Niu, Jianfu Zhang +1
Few-shot image generation and few-shot image translation are two related tasks, both of which aim to generate new images for an unseen category with only a few images. In this work…
Human-centric Image Cropping with Partition-aware and Content-preserving Features
Bo Zhang, Li Niu, Xing Zhao +1
Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task. In this paper, we consider a specific and practical application: human…
Spatial Transformation for Image Composition via Correspondence Learning
Bo Zhang, Yue Liu, Kaixin Lu +2
When using cut-and-paste to acquire a composite image, the geometry inconsistency between foreground and background may severely harm its fidelity. To address the geometry inconsis…
From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering
Jiangtong Li, Li Niu, Liqing Zhang
Video understanding has achieved great success in representation learning, such as video caption, video object grounding, and video descriptive question-answer. However, current me…
Deep Video Harmonization with Color Mapping Consistency
Xinyuan Lu, Shengyuan Huang, Li Niu +2
Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention an…
XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Zhangxuan Gu, Changhua Meng, Ke Wang +4
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout info…
STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation
Zhengkai Jiang, Zhangxuan Gu, Jinlong Peng +6
Video Instance Segmentation (VIS) is a task that simultaneously requires classification, segmentation, and instance association in a video. Recent VIS approaches rely on sophistica…
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
Yan Liu, Zhijie Zhang, Li Niu +2
Object detection has achieved promising success, but requires large-scale fully-annotated data, which is time-consuming and labor-extensive. Therefore, we consider object detection…