bcmi

A curated list of papers, code and resources pertaining to image composition/compositing or object/subject insertion/addition/compositing, which aims to generate realistic composite image.

Image composition toolbox: everything you want to know about image composition/compositing or object/subject insertion/addition/compositing.

[CVPR 2020] The first large-scale public benchmark dataset for image harmonization. The code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for...

A curated list of papers, code and resources pertaining to image composition/compositing or object/subject insertion/addition/compositing, which aims to generate realistic composite image.

A curated list of papers, code and resources pertaining to image harmonization.

[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.

A curated list of papers, code and resources pertaining to few-shot image generation.

[ACM MM 2021] Visible Watermark Removal via Self-calibrated Localization and Background Refinement

Code for our ACMMM2020 paper "Context-aware Feature Generation for Zero-shot Semantic Segmentation".

[AAAI 2026] CareCom: Generative Image Composition with Calibrated Reference Features

A controllable image composition model which could be used for image blending, image harmonization, view synthesis.

A curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.

[BMVC2021] The first image composition assessment dataset. Used in the paper "Image Composition Assessment with Saliency-augmented Multi-pattern Pooling". Useful for image composition assessment,...

[AAAI 2022] The first dataset on foreground object shadow generation for image composition in real-world scenes. The code used in our paper "Shadow Generation for Composite Image in Real-world...

[CVPR 2024] The dataset, code, and model for our paper "Shadow Generation for Composite Image Using Diffusion Model", CVPR, 2024.

The code for "A Single Simple Patch is All You Need for AI-generated Image Detection"

A curated list of papers, code, and resources pertaining to generative image composition or object insertion.

[CVPR 2025] The code and model for our paper "Shadow Generation Using Diffusion Model with Geometry Prior", CVPR, 2025.

[CVPR 2022] We unify pixel-to-pixel transformation and color-to-color transformation in a coherent framework for high-resolution image harmonization. We also release 100 high-resolution real...

A curated list of papers, code, and resources pertaining to object shadow generation.

[ECCV 2026] The dataset, code, and model for our paper "In-context Region-based Drag: Drag Any Region to Any Shape"

A curated list of papers, code, and resources pertaining to object placement.

An unofficial implementation of the paper "ObjectStitch: Object Compositing with Diffusion Model", CVPR 2023.

[ECCV 2022] Official code for "Learning Object Placement via Dual-path Graph Completion"

Comprehensive Dataset for Image Composition & Object Insertion

The first dataset of composite images with rationality score indicating whether the object placement in a composite image is reasonable.

Fusing-and-Filling GAN (F2GAN) for few-shot image generation, ACM MM2020

BargainNet: Background-Guided Domain Translation for Image Harmonization. Useful for Image harmonization, image composition, etc.

[CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. The code used in our paper "From Representation to Reasoning:...

[IJCAI 2022] The first public benchmark dataset for video harmonization. The code used in our paper "Deep Video Harmonization with Color Mapping Consistency", IJCAI 2022.

[CVPR 2026] Fine-Grained GRPO for Precise Preference Alignment in Flow Models

[NeurIPS 2021] The first weak-shot classification paper.

[ACM MM 2023] The code used in our paper "Painterly Image Harmonization using Diffusion Model", ACM MM2023.

The dataset, code, and model for our paper "Reflection Generation for Composite Image Using Diffusion Model", ICME, 2026.

[AAAI 2023] Painterly image harmonization in both spatial domain and frequency domain.

[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

[ECCV 2022] Generate sample-specific intra-category deltas for few-shot image generation.

A curated list of papers, code and resources pertaining to image blending.