Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions Paper β’ 2604.23774 β’ Published 26 days ago β’ 16
Video Analysis and Generation via a Semantic Progress Function Paper β’ 2604.22554 β’ Published Apr 24 β’ 63
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers Paper β’ 2603.28762 β’ Published Mar 30 β’ 25
RealMaster: Lifting Rendered Scenes into Photorealistic Video Paper β’ 2603.23462 β’ Published Mar 24 β’ 33
SemanticMoments: Training-Free Motion Similarity via Third Moment Features Paper β’ 2602.09146 β’ Published Feb 9 β’ 21
Running on Zero Agents 36 POps Space π» 36 Create images by combining objects, textures, and scenes
Running on Zero Agents Featured 826 ZoeDepth π¦ 826 Generate depth maps and 3D views from a single image