110 citations · 365 across the 58 of their papers we have counts for
57 papers · 1 filter
Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering
Zhaohe Liao, Jiangtong Li, Li Niu +1
Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes…
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…
ControlCom: Controllable Image Composition using Diffusion Model
Bo Zhang, Yuxuan Duan, Jun Lan +4
Image composition targets at synthesizing a realistic composite image from a pair of foreground and background images. Recently, generative composition methods are built on large p…
DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
Qingyang Liu, Jianting Wang, Li Niu
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadow for the inserte…
Foreground Object Search by Distilling Composite Image Feature
Bo Zhang, Jiacheng Sui, Li Niu
Foreground object search (FOS) aims to find compatible foreground objects for a given background image, producing realistic composite image. We observe that competitive retrieval p…
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…
Scene-aware Human Pose Generation using Transformer
Jieteng Yao, Junjie Chen, Li Niu +1
Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics. In this paper,…
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…
Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
Xinhao Tao, Junyan Cao, Yan Hong +1
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the insert…
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…
Painterly Image Harmonization in Dual Domains
Junyan Cao, Yan Hong, Li Niu
Image harmonization aims to produce visually harmonious composite images by adjusting the foreground appearance to be compatible with the background. When the composite image has p…
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…
Inharmonious Region Localization by Magnifying Domain Discrepancy
Jing Liang, Li Niu, Penghao Wu +2
Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the…
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…