5 papers · 1 filter
RealMaster: Lifting Rendered Scenes into Photorealistic Video
Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun +5
State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Fu…
ShapeUP: Scalable Image-Conditioned 3D Editing
Inbar Gat, Dana Cohen-Bar, Guy Levy +2
Recent advancements in 3D foundation models have enabled the generation of high-fidelity assets, yet precise 3D manipulation remains a significant challenge. Existing 3D editing fr…
IP-Composer: Semantic Composition of Visual Concepts
Sara Dorfman, Dana Cohen-Bar, Rinon Gal +1
Content creators often draw inspiration from multiple visual sources, combining distinct elements to craft new compositions. Modern computational approaches now aim to emulate this…
Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation
Yiftach Edelstein, Or Patashnik, Dana Cohen-Bar +1
Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an obj…
Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes
Dana Cohen-Bar, Elad Richardson, Gal Metzer +2
Recent breakthroughs in text-guided image generation have led to remarkable progress in the field of 3D synthesis from text. By optimizing neural radiance fields (NeRF) directly fr…