Soroush Mehraban

STARS (WACV'26) Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences.

Soroush Mehraban

FastHMR (WACV'26)Accelerating Human Mesh Recovery via Token & Layer Merging with Diffusion Decoding

Soroush Mehraban

TRELLIS One Latent for Any 3D Asset

Soroush Mehraban

LightlyTrain - Train Better Models, Faster - No Labels Needed

Soroush Mehraban

One-step Diffusion with Distribution Matching Distillation

Soroush Mehraban

Variational Score Distillation (VSD) Helps Create Amazing 3D Scenes From Text Prompts

Soroush Mehraban

Dream-in-4D Paper Explained!

Soroush Mehraban

FreeU - Paper Explained

Soroush Mehraban

AnimateDiff - Paper explained!

Soroush Mehraban

DreamFusion Text-to-3D using 2D Diffusion

Soroush Mehraban

Null-text Inversion for Editing Real Images using Guided Diffusion Models

Soroush Mehraban

Prompt-to-Prompt (P2P) image Editing - Method Explained

Soroush Mehraban

Denoising Diffusion Null-Space Model (DDNM) - Method Explained

Soroush Mehraban

Autoregressive Image Generation without Vector Quantization

Soroush Mehraban

Diffusion Models (DDPM & DDIM) - Easily explained!

Soroush Mehraban

GLIGEN (CVPR2023) Open-Set Grounded Text-to-Image Generation

Soroush Mehraban

The Entropy Enigma Success and Failure of Entropy Minimization

Soroush Mehraban

Tent Fully Test-time Adaptation by Entropy Minimization

Soroush Mehraban

VPD (ICCV2023) Unleashing Text-to-Image Diffusion Models for Visual Perception

Soroush Mehraban

TokenHMR (CVPR2024) Advancing Human Mesh Recovery witha Tokenized Pose Representation

Soroush Mehraban

SHViT (CVPR2024) Single-Head Vision Transformer with Memory Efficient Macro Design

Soroush Mehraban

InstaFlow One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

Soroush Mehraban

FastV An Image is Worth 12 Tokens After Layer 2

Soroush Mehraban

GaLore Memory-Efficient LLM Training by Gradient Low-Rank Projection

Soroush Mehraban

PoseGPT (ChatPose) Chatting about 3D Human Pose

Soroush Mehraban

MotionAGFormer (WACV2024) Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network

Soroush Mehraban

HD-GCN (ICCV2023) Skeleton-Based Action Recognition

Soroush Mehraban

ST-GCN Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Soroush Mehraban

Graph Convolutional Networks (GCN) From CNN point of view

Soroush Mehraban

DINO Self-Supervised Vision Transformers

Soroush Mehraban