9 papers
Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment
Xin Lei Lin, Soroush Mehraban, Abhishek Moturu +1
Automated pain assessment from facial expressions is crucial for non-communicative patient. Progress has been limited by two challenges: (i) existing datasets exhibit severe demogr…
GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain
Vida Adeli, Soroush Mehraban, Majid Mirmehdi +6
Gait analysis is crucial for the diagnosis and monitoring of movement disorders like Parkinson's Disease. While computer vision models have shown potential for objectively evaluati…
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Soroush Mehraban, Mohammad Javad Rajabi, Andrea Iaboni +1
Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike con…
Token Perturbation Guidance for Diffusion Models
Javad Rajabi, Soroush Mehraban, Seyedmorteza Sadat +1
Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG req…
FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding
Soroush Mehraban, Andrea Iaboni, Babak Taati
Recent transformer-based models for 3D Human Mesh Recovery (HMR) have achieved strong performance but often suffer from high computational cost and complexity due to deep transform…
PickStyle: Video-to-Video Style Transfer with Context-Style Adapters
Soroush Mehraban, Vida Adeli, Jacob Rommann +4
We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in a target style specified by a t…