10 papers
IntrinSync: Joint Intrinsic Decomposition and Reciprocal Rendering
Zheng Gu, Rui Huang, Xilu Zhang +6
Inverse rendering decomposes an image into intrinsic properties such as appearance, illumination, geometry, and material, yet these properties are inherently interdependent. A reli…
Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
Zhihao Wen, Yixin Yang, Bojian Wu +4
While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging.…
Complexity-Balanced Diffusion Splitting
Noam Issachar, Dani Lischinski, Raanan Fattal
Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to intricate data distributions…
Cycle-Consistent Tuning for Layered Image Decomposition
Zheng Gu, Min Lu, Zhida Sun +3
Disentangling visual layers in real-world images is a persistent challenge in vision and graphics, as such layers often involve non-linear and globally coupled interactions, includ…
DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
Noam Issachar, Guy Yariv, Sagie Benaim +3
Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention…
Palette Aligned Image Diffusion
Elad Aharoni, Noy Porat, Dani Lischinski +1
We introduce the Palette-Adapter, a novel method for conditioning text-to-image diffusion models on a user-specified color palette. While palettes are a compact and intuitive tool…
EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits
Ron Yosef, Moran Yanuka, Yonatan Bitton +1
Text-guided image editing, fueled by recent advancements in generative AI, is becoming increasingly widespread. This trend highlights the need for a comprehensive framework to veri…
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
Aviv Slobodkin, Hagai Taitelbaum, Yonatan Bitton +7
Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject ima…
Seed-to-Seed: Unpaired Image Translation in Diffusion Seed Space
Or Greenberg, Eran Kishon, Dani Lischinski
We introduce Seed-to-Seed Translation (StS), a novel approach that combines GANs and diffusion models (DMs) for unpaired Image-to-Image Translation. Our approach is aimed at global…
S2ST: Image-to-Image Translation in the Seed Space of Latent Diffusion
Or Greenberg, Eran Kishon, Dani Lischinski
Image-to-image translation (I2IT) refers to the process of transforming images from a source domain to a target domain while maintaining a fundamental connection in terms of image…