Matting by generation

Z Wang, B Li, J Wang, YL Liu, J Gu… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
This paper introduces an innovative approach for image matting that redefines the traditional
regression-based task as a generative modeling challenge. Our method harnesses the …

Cross-image attention for zero-shot appearance transfer

Y Alaluf, D Garibi, O Patashnik… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
Recent advancements in text-to-image generative models have demonstrated a remarkable
ability to capture a deep semantic understanding of images. In this work, we leverage this …

Surgicalsam: Efficient class promptable surgical instrument segmentation

W Yue, J Zhang, K Hu, Y Xia, J Luo… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
The Segment Anything Model (SAM) is a powerful foundation model that has revolutionised
image segmentation. To apply SAM to surgical instrument segmentation, a common …

Alignsam: Aligning segment anything model to open context via reinforcement learning

D Huang, X Xiong, J Ma, J Li, Z Jie… - Proceedings of the …, 2024 - openaccess.thecvf.com
Powered by massive curated training data Segment Anything Model (SAM) has
demonstrated its impressive generalization capabilities in open-world scenarios with the …

Conform: Contrast is all you need for high-fidelity text-to-image diffusion models

THS Meral, E Simsar, F Tombari… - Proceedings of the …, 2024 - openaccess.thecvf.com
Images produced by text-to-image diffusion models might not always faithfully represent the
semantic intent of the provided text prompt where the model might overlook or entirely fail to …

Initno: Boosting text-to-image diffusion models via initial noise optimization

X Guo, J Liu, M Cui, J Li, H Yang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent strides in the development of diffusion models exemplified by advancements such as
Stable Diffusion have underscored their remarkable prowess in generating visually …

R&b: Region and boundary aware zero-shot grounded text-to-image generation

J Xiao, H Lv, L Li, S Wang, Q Huang - arXiv preprint arXiv:2310.08872, 2023 - arxiv.org
Recent text-to-image (T2I) diffusion models have achieved remarkable progress in
generating high-quality images given text-prompts as input. However, these models fail to …

Migc++: Advanced multi-instance generation controller for image synthesis

D Zhou, Y Li, F Ma, Z Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We introduce the Multi-Instance Generation (MIG) task, which focuses on generating
multiple instances within a single image, each accurately placed at predefined positions with …

Quantum circuit synthesis with diffusion models

F Fürrutter, G Muñoz-Gil, HJ Briegel - Nature Machine Intelligence, 2024 - nature.com
Quantum computing has recently emerged as a transformative technology. Yet, its promised
advantages rely on efficiently translating quantum operations into viable physical …

Diffusion for natural image matting

Y Hu, Y Lin, W Wang, Y Zhao, Y Wei, H Shi - European Conference on …, 2025 - Springer
Existing natural image matting algorithms inevitably have flaws in their predictions on
difficult cases, and their one-step prediction manner cannot further correct these errors. In …