Yusuf Dalva

21 papers A* 3Journal 17Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Canvas-to-Image: Compositional Image Generation with Multimodal Controls.
CoRR
Yusuf Dalva, Guocheng Gordon Qian, Maya Goldenberg, Tsai-Shien Chen, Kfir Aberman, Sergey Tulyakov, Pinar Yanardag, Kuan-Chieh Jackson Wang
2025 A* conf
FluxSpace: Disentangled Semantic Editing in Rectified Flow Models.
CVPR
Yusuf Dalva, Kavana Venkatesh, Pinar Yanardag
2025 J jnl
LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas.
CoRR
Guocheng Gordon Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva, Anujraaj Goyal, Willi Menapace, Ivan Skorokhodov, Meng Dong, Arpit Sahni, Daniil Ostashev, Ju Hu, Sergey Tulyakov, Kuan-Chieh Jackson Wang
2025 J jnl
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers.
CoRR
Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag
2024 J jnl
Benchmarking the Robustness of Instance Segmentation Models.
IEEE Trans. Neural Networks Learn. Syst.
Yusuf Dalva, Hamza Pehlivan, Said Fahri Altindis, Aysegul Dundar
2024 J jnl
Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG.
CoRR
Kavana Venkatesh, Yusuf Dalva, Ismini Lourentzou, Pinar Yanardag
2024 J jnl
FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers.
CoRR
Yusuf Dalva, Kavana Venkatesh, Pinar Yanardag
2024 J jnl
GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models.
CoRR
Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag
2024 J jnl
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors.
CoRR
Yusuf Dalva, Yijun Li, Qing Liu, Nanxuan Zhao, Jianming Zhang, Zhe Lin, Pinar Yanardag
2024 A* conf
NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models.
CVPR
Yusuf Dalva, Pinar Yanardag
2024 J jnl
Refining 3D Human Texture Estimation From a Single Image.
IEEE Trans. Pattern Anal. Mach. Intell.
Said Fahri Altindis, Adil Meric, Yusuf Dalva, Ugur Güdükbay, Aysegul Dundar
2024 J jnl
The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP.
CoRR
Hidir Yesiltepe, Yusuf Dalva, Pinar Yanardag
2023 J jnl
Face Attribute Editing with Disentangled Latent Vectors.
CoRR
Yusuf Dalva, Hamza Pehlivan, Cansu Moran, Öykü Irmak Hatipoglu, Aysegül Dündar
2023 J jnl
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing.
IEEE Trans. Pattern Anal. Mach. Intell.
Yusuf Dalva, Hamza Pehlivan, Öykü Irmak Hatipoglu, Cansu Moran, Aysegul Dundar
2023 J jnl
NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models.
CoRR
Yusuf Dalva, Pinar Yanardag
2023 J jnl
Refining 3D Human Texture Estimation from a Single Image.
CoRR
Said Fahri Altindis, Adil Meric, Yusuf Dalva, Ugur Güdükbay, Aysegül Dündar
2023 A* conf
StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN.
CVPR
Hamza Pehlivan, Yusuf Dalva, Aysegul Dundar
2022 J jnl
StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN.
CoRR
Hamza Pehlivan, Yusuf Dalva, Aysegul Dundar
2022 — conf
VecGAN: Image-to-Image Translation with Interpretable Latent Directions.
ECCV (16)
Yusuf Dalva, Said Fahri Altindis, Aysegul Dundar
2022 J jnl
VecGAN: Image-to-Image Translation with Interpretable Latent Directions.
CoRR
Yusuf Dalva, Said Fahri Altindis, Aysegul Dundar
2021 J jnl
Benchmarking the Robustness of Instance Segmentation Models.
CoRR
Said Fahri Altindis, Yusuf Dalva, Aysegul Dundar