D
Dani Lischinski
Researcher at Hebrew University of Jerusalem
Publications - 158
Citations - 20287
Dani Lischinski is an academic researcher from Hebrew University of Jerusalem. The author has contributed to research in topics: Computer science & Image segmentation. The author has an hindex of 52, co-authored 147 publications receiving 17600 citations. Previous affiliations of Dani Lischinski include Cornell University & University of Washington.
Papers
More filters
Constrained Synthesis of Textural Motion for Animation
Shmuel Moradoff,Dani Lischinski +1 more
TL;DR: This work proposes a new simple technique for generating constrained variations of different lengths from an existing captured or otherwise animated motion, applicable to textural motions, where the motion sequence can be decomposed into shorter motion segments without an obvious temporal ordering among them.
Journal ArticleDOI
Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields
Omri Avrahami,Dani Lischinski +1 more
TL;DR: Blended-NeRF as mentioned in this paper uses a pre-trained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene.
Journal ArticleDOI
SVNR: Spatially-variant Noise Removal with Denoising Diffusion
Naama Pearl,Ya. A. Brodsky,Dana Berman,Assaf Zomet,A. Rav-Acha,Daniel Cohen-Or,Dani Lischinski +6 more
TL;DR: SVNR as mentioned in this paper proposes to use the noisy input image as the starting point for the denoising diffusion process, in addition to conditioning the process on it, and adapt the diffusion process to allow each pixel to have its own time embedding, and propose training and inference schemes that support spatially-varying time maps.
Proceedings ArticleDOI
Affinity-based constraint optimization for nearly-automatic vessel segmentation
TL;DR: In this paper, an affinity-based optimization method for nearly automatic vessel segmentation in CTA scans is presented, where the desired segmentation is modeled as a function that minimizes a quadratic affinity based functional, which incorporates intensity and geometrical vessel shape information and a smoothing constraint.
Posted Content
Evaluation and Comparison of Edge-Preserving Filters.
TL;DR: In this paper, the authors introduce a systematic methodology for evaluating and comparing edge-preserving filters and demonstrate it on a diverse set of published edge preserving filters, and present a common baseline along which a comparison of different operators can be achieved and use it to determine equivalent parameter mappings between methods.