Search Results for author: Shant Navasardyan

Found 9 papers, 6 papers with code

Video Instance Matting

1 code implementation7 Nov 2023 Jiachen Li, Roberto Henschel, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Humphrey Shi

To remedy this deficiency, we propose Video Instance Matting~(VIM), that is, estimating alpha mattes of each instance at each frame of a video sequence.

Binarization Image Matting +4

Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else

no code implementations11 Oct 2023 Hazarapet Tunanyan, Dejia Xu, Shant Navasardyan, Zhangyang Wang, Humphrey Shi

To achieve this goal, we identify the limitations in the text embeddings used for the pre-trained text-to-image diffusion models.

Image Manipulation

MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

1 code implementation ICCV 2023 Andranik Sargsyan, Shant Navasardyan, Xingqian Xu, Humphrey Shi

In this paper we present a simple image inpainting baseline, Mobile Inpainting GAN (MI-GAN), which is approximately one order of magnitude computationally cheaper and smaller than existing state-of-the-art inpainting models, and can be efficiently deployed on mobile devices.

Efficient Neural Network Image Inpainting +1

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

no code implementations CVPR 2023 Haoming Lu, Hazarapet Tunanyan, Kai Wang, Shant Navasardyan, Zhangyang Wang, Humphrey Shi

Diffusion models have demonstrated impressive capability of text-conditioned image synthesis, and broader application horizons are emerging by personalizing those pretrained diffusion models toward generating some specialized target object or style.

Disentanglement Image Generation

Mask Matching Transformer for Few-Shot Segmentation

1 code implementation5 Dec 2022 Siyu Jiao, Gengwei Zhang, Shant Navasardyan, Ling Chen, Yao Zhao, Yunchao Wei, Humphrey Shi

Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results.

Few-Shot Semantic Segmentation Segmentation

Image Completion with Heterogeneously Filtered Spectral Hints

1 code implementation7 Nov 2022 Xingqian Xu, Shant Navasardyan, Vahram Tadevosyan, Andranik Sargsyan, Yadong Mu, Humphrey Shi

We also prove the effectiveness of our design via ablation studies, from which one may notice that the aforementioned challenges, i. e. pattern unawareness, blurry textures, and structure distortion, can be noticeably resolved.

Image Inpainting

VMFormer: End-to-End Video Matting with Transformer

1 code implementation26 Aug 2022 Jiachen Li, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Yunchao Wei, Humphrey Shi

In this paper, we propose VMFormer: a transformer-based end-to-end method for video matting.

Video Matting

Image Inpainting with Onion Convolutions

no code implementations4 Dec 2020 Shant Navasardyan, Marianna Ohanyan

The concept of onion convolution is introduced with the purpose of preserving feature continuities and semantic coherence.

Image Inpainting

Cannot find the paper you are looking for? You can Submit a new open access paper.