4 papers
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +1
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using nat…
CineLOG: A Training Free Approach for Cinematic Long Video Generation
Zahra Dehghanian, Morteza Abolghasemi, Hamid Beigy +1
Controllable video synthesis is a central challenge in computer vision, yet current models struggle with fine grained control beyond textual prompts, particularly for cinematic att…
Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS
Mahta Fetrat, Donya Navabi, Zahra Dehghanian +2
Lightweight, real-time text-to-speech systems are crucial for accessibility. However, the most efficient TTS models often rely on lightweight phonemizers that struggle with context…
LensCraft: Your Professional Virtual Cinematographer
Zahra Dehghanian, Morteza Abolghasemi, Hossein Azizinaghsh +3
Digital creators, from indie filmmakers to animation studios, face a persistent bottleneck: translating their creative vision into precise camera movements. Despite significant pro…