activity
20242026
collaborators

5 papers

cs.CV2026

Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

Martin Rath, Morteza Ghahremani, Yitong Li +3

Computed tomography (CT) provides rich 3D anatomical details but is often constrained by high radiation exposure, substantial costs, and limited availability. While standard chest…

cs.CV2026

Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades

Ashkan Taghipour, Morteza Ghahremani, Zinuo Li +3

Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally…

cs.CV2025

SVR-GS: Spatially Variant Regularization for Probabilistic Masks in 3D Gaussian Splatting

Ashkan Taghipour, Vahid Naghshin, Benjamin Southwell +3

3D Gaussian Splatting (3DGS) enables fast, high-quality novel view synthesis but typically relies on densification followed by pruning to optimize the number of Gaussians. Existing…

cs.CV2025

LatentMove: Towards Complex Human Movement Video Generation

Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun +5

Image-to-video (I2V) generation seeks to produce realistic motion sequences from a single reference image. Although recent methods exhibit strong temporal consistency, they often s…

cs.CV2024

Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions

Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun +4

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational…