works on

From the 1 of 13 linked papers with an AI index.

collaborators

13 papers

cs.CV2026

MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians

Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +1

The paper introduces a training‑free pipeline that separates 3D geometry reconstruction from semantic labeling to create compact, object‑level semantic maps from a single monocular…

eess.IV2026

3DLAND: 3D Lesion Abdominal Anomaly Localization Dataset

Mehran Advand, Zahra Dehghanian, Navid Faraji +3

Existing medical imaging datasets for abdominal CT often lack three-dimensional annotations, multi-organ coverage, or precise lesion-to-organ associations, hindering robust represe…

cs.LG2025

ReDiF: Reinforced Distillation for Few Step Diffusion

Amirhossein Tighkhorshid, Zahra Dehghanian, Gholamali Aminian +2

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In thi…

cs.CV2025

RealDrag: The First Dragging Benchmark with Real Target Image

Ahmad Zafarani, Zahra Dehghanian, Mohammadreza Davoodi +3

The evaluation of drag based image editing models is unreliable due to a lack of standardized benchmarks and metrics. This ambiguity stems from inconsistent evaluation protocols an…

cs.CV2025

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…

cs.SD2025

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…