Name: BCMI
Type: Organization
Bio: Center for Brain-Like Computing and Machine Intelligence, Shanghai Jiao Tong University.
Location: 3-East 307 SEIEE Building, No. 800 Dongchuan Road. Minhang District, Shanghai, 200240
Blog: www.ustcnewly.com
BCMI's Projects
A virtual accessory try-on dataset which could be used for image composition
anormal detection of time series data.
[AAAI2024] Painterly Image Harmonization by Learning from Painterly Objects
[BMVC2022] Inharmonious Region Localization with Auxiliary Style Feature
A curated list of papers, code and resources pertaining to few-shot image generation.
A curated list of papers, code, and resources pertaining to foreground object search.
A curated list of papers, code, and resources pertaining to generative image composition or object insertion.
A curated list of papers, code and resources pertaining to image blending.
A curated list of papers, code and resources pertaining to image composition/compositing or object insertion, which aims to generate realistic composite image.
A curated list of papers, code and resources pertaining to image harmonization.
A curated list of papers, code, and resources pertaining to object placement.
A curated list of papers, code, and resources pertaining to object shadow generation.
A curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.
BargainNet: Background-Guided Domain Translation for Image Harmonization. Useful for Image harmonization, image composition, etc.
Code for our ACMMM2020 paper "Context-aware Feature Generation for Zero-shot Semantic Segmentation".
Code for "From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation".
[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: Towards both Evidence and Commonsense Reasoning for Video Question-Answering", CVPR2022.
[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 composite images for evaluation.
Summarize different color transfer strategies for image harmonization task.
A controllable image composition model which could be used for image blending, image harmonization, view synthesis.
[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.
[ECCV 2022] Generate sample-specific intra-category deltas for few-shot image generation.
[ICME2021]The first work on Deep Inharmonious Region Localization, which can help image harmonization in an adversarial way.
A simple baseline for image composition using text-guided inpainting model
[ACM MM 23] Deep image harmonization in Dual Color Space
Extendible Generic Anomaly Detection System