Search Results for author:
Found 76 papers, 47 papers with code
Shadow Generation for Composite Image Using Diffusion model
In the realm of image composition, generating realistic shadow for the inserted foreground remains a formidable challenge.
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE.
A Single Simple Patch is All You Need for AI-generated Image Detection
The recent development of generative models unleashes the potential of generating hyper-realistic fake images.
Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles
Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background.
Painterly Image Harmonization by Learning from Painterly Objects
In particular, we learn a mapping from background style and object information to object style based on painterly objects in artistic paintings.
Painterly Image Harmonization via Adversarial Residual Learning
In this work, we employ adversarial learning to bridge the domain gap between foreground feature map and background feature map.
Virtual Accessory Try-On via Keypoint Hallucination
Specifically, our approach learns the human body priors and hallucinates the target locations of specified foreground keypoints in the background.
DreamCom: Finetuning Text-guided Inpainting Model for Image Composition
The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image.
DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic.
ControlCom: Controllable Image Composition using Diffusion Model
To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition.
Foreground Object Search by Distilling Composite Image Feature
Additionally, previous works did not release their datasets, so we contribute two datasets for FOS task: S-FOSD dataset with synthetic composite images and R-FOSD dataset with real composite images.
Deep Image Harmonization in Dual Color Spaces
The network comprises a $RGB$ harmonization backbone, an $Lab$ encoding module, and an $Lab$ control module.
Ranked #1 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Scene-aware Human Pose Generation using Transformer
Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics.
Painterly Image Harmonization using Diffusion Model
Painterly image harmonization aims to insert photographic objects into paintings and obtain artistically coherent composite images.
Deep Image Harmonization with Learnable Augmentation
In particular, our designed SYthetic COmposite Network (SycoNet) takes in a real image with foreground mask and a random vector to learn suitable color transformation, which is applied to the foreground of this real image to produce a synthetic composite image.
Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation
Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background.
Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction.
WeditGAN: Few-Shot Image Generation via Latent Space Relocation
In this work, we introduce WeditGAN, which realizes model transfer by editing the intermediate latent codes $w$ in StyleGANs with learned constant offsets ($\Delta w$), discovering and constructing target latent spaces via simply relocating the distribution of source latent spaces.
Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation
First, we train a data-efficient StyleGAN2 on defect-free images as the backbone.
Image Cropping With Spatial-Aware Feature and Rank Consistency
To address the first issue, we propose spatial-aware feature to encode the spatial relationship between candidate crops and aesthetic elements, by feeding the concatenation of crop mask and selectively aggregated feature maps to a light-weighted encoder.
Fine-grained Visible Watermark Removal
Visible watermark removal aims to erase the watermark from watermarked image and recover the background image, which is a challenging task due to the diverse watermarks.
Knowledge Proxy Intervention for Deconfounded Video Question Answering
To tackle the challenge that the confounder in VideoQA is unobserved and non-enumerable in general, we propose a model-agnostic framework called Knowledge Proxy Intervention (KPI), which introduces an extra knowledge proxy variable in the causal graph to cut the backdoor path and remove the confounder.
Painterly Image Harmonization in Dual Domains
In this work, we propose a novel painterly harmonization network consisting of a dual-domain generator and a dual-domain discriminator, which harmonizes the composite image in both spatial domain and frequency domain.
Video Object of Interest Segmentation
Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are relevant to the target image.
Weak-shot Semantic Segmentation via Dual Similarity Transfer
Proposal segmentation allows proposal-pixel similarity transfer from base classes to novel classes, which enables the mask learning of novel classes.
Inharmonious Region Localization via Recurrent Self-Reasoning
Synthetic images created by image editing operations are prevalent, but the color or illumination inconsistency between the manipulated region and background may make it unrealistic.
Inharmonious Region Localization with Auxiliary Style Feature
Based on the extracted style features, we also propose a novel style voting module to guide the localization of inharmonious region.
Inharmonious Region Localization by Magnifying Domain Discrepancy
Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background.
Learning Object Placement via Dual-path Graph Completion
Object placement aims to place a foreground object over a background image with a suitable location and size.
Few-shot Image Generation Using Discrete Content Representation
Few-shot image translation disentangles an image into style vector and content map.
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork.
Human-centric Image Cropping with Partition-aware and Content-preserving Features
Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task.
Spatial Transformation for Image Composition via Correspondence Learning
Instead, we propose a novel correspondence learning network (CorrelNet) to model the correspondence between foreground and background using cross-attention maps, based on which we can predict the target coordinate that each source coordinate of foreground should be mapped to on the background.
CcHarmony: Color-checker based Image Harmonization Dataset
Image harmonization targets at adjusting the foreground in a composite image to make it compatible with the background, producing a more realistic and harmonious image.
From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering
We hope that Causal-VidQA can guide the research of video understanding from representation learning to deeper reasoning.
Fast Object Placement Assessment
However, given a pair of scaled foreground and background, to enumerate all the reasonable locations, existing OPA model needs to place the foreground at each location on the background and pass the obtained composite image through the model one at a time, which is very time-consuming.
Deep Video Harmonization with Color Mapping Consistency
Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background.
Dual-Path Image Inpainting With Auxiliary GAN Inversion
Different from feed-forward methods, they seek for a closest latent code to the corrupted image and feed it to a pretrained generator.
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories.
Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
Deep learning is a data-hungry approach, which requires massive training data.
Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary
As a result, we find that pixel-level annotation of base categories can facilitate affinity learning and propagation, leading to higher-quality CAMs of novel categories.
HYouTube: Video Harmonization Dataset
In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos.
High-Resolution Image Harmonization via Collaborative Dual Transformations
Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context.
Ranked #3 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Visible Watermark Removal via Self-calibrated Localization and Background Refinement
In the refinement stage, we integrate multi-level features to improve the texture quality of watermarked area.
OPA: Object Placement Assessment Dataset
Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e. g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image.
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
We have also contributed the first image composition toolbox: libcom https://github. com/bcmi/libcom, which assembles 10+ image composition related functions (e. g., image blending, image harmonization, object placement, shadow generation, generative composition).
End-to-End Video Object Detection with Spatial-Temporal Transformers
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Shadow Generation for Composite Image in Real-world Scenes
In this work, we focus on generating plausible shadow for the foreground object in the composite image.
Inharmonious Region Localization
The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background.
Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image.
Ranked #1 on
Aesthetics Quality Assessment
on CADB
Deep Image Harmonization by Bridging the Reality Gap
Image harmonization has been significantly advanced with large-scale harmonization dataset.
Parallel Multi-Resolution Fusion Network for Image Inpainting
Conventional deep image inpainting methods are based on auto-encoder architecture, in which the spatial details of images will be lost in the down-sampling process, leading to the degradation of generated results.
Disentangled Information Bottleneck
The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that balances the compression and prediction terms.
From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories.
Weak-shot Fine-grained Classification via Similarity Transfer
In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories.
BargainNet: Background-Guided Domain Translation for Image Harmonization
Therefore, we propose an image harmonization network with a novel domain code extractor and well-tailored triplet losses, which could capture the background domain information to guide the foreground harmonization.
Ranked #13 on
Image Harmonization
on iHarmony4
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork.
Context-aware Feature Generation for Zero-shot Semantic Segmentation
In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.
F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
In this paper, we propose a Fusing-and-Filling Generative Adversarial Network (F2GAN) to generate realistic and diverse images for a new category with only a few images.
Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets
To address these issues, we propose our MTL with Selective Augmentation (MTL-SA) method to select the training samples in unlabeled datasets with confident pseudo labels and close data distribution to the labeled dataset.
MatchingGAN: Matching-based Few-shot Image Generation
Matching generator can match random vectors with a few conditional images from the same category and generate new images for this category based on the fused features.
Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition
Specifically, the VRE module includes a proxy task which imposes pseudo motion label constraint and temporal coherence constraint on unlabeled videos, while the MRA module could predict the motion information of a static action image by exploiting unlabeled videos.
Zero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement
The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketches to retrieve images of the same category from a natural image gallery.
DoveNet: Deep Image Harmonization via Domain Verification
Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.
Ranked #6 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Image Cropping with Composition and Saliency Aware Aesthetic Score Map
Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image.
A Proposal-based Approach for Activity Image-to-Video Retrieval
Activity image-to-video retrieval task aims to retrieve videos containing the similar activity as the query image, which is a challenging task because videos generally have many background segments irrelevant to the activity.
Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.
Learning from Web Data with Self-Organizing Memory Module
However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively.
Ranked #14 on
Image Classification
on WebVision-1000
Hard Pixel Mining for Depth Privileged Semantic Segmentation
Specifically, we propose a novel Loss Weight Module, which outputs a loss weight map by employing two depth-related measurements of hard pixels: Depth Prediction Error and Depthaware Segmentation Error.
Fine-grained Classification using Heterogeneous Web Data and Auxiliary Categories
In the extreme case, given a set of test categories without any well-labeled training data, the majority of existing works can be grouped into the following two research directions: 1) crawl noisy labeled web data for the test categories as training data, which is dubbed as webly supervised learning; 2) transfer the knowledge from auxiliary categories with well-labeled training data to the test categories, which corresponds to zero-shot learning setting.
Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification
The drawbacks of the above two directions motivate us to design a new framework which can jointly leverage both web data and auxiliary labeled categories to predict the test categories that are not associated with any well-labeled training images.
Learning from Noisy Web Data with Category-level Supervision
As tons of photos are being uploaded to public websites (e. g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also referred to as webly supervised learning.
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities.
Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic mapping between the low-level visual feature space and the intermediate semantic space.
Multi-View Domain Generalization for Visual Recognition
Considering the recent works show the domain generalization capability can be enhanced by fusing multiple SVM classifiers, we build upon exemplar SVMs to learn a set of SVM classifiers by using one positive sample and all negative samples in the source domain each time.
Visual Recognition by Learning From Web Data: A Weakly Supervised Domain Generalization Approach
In this work, we formulate a new weakly supervised domain generalization problem for the visual recognition task by using loosely labeled web images/videos as training data.
