activity
20242026
collaborators

9 papers

cs.CV2026

Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation

Muhammad Saif Ullah Khan, Chen-Yu Wang, Tim Prokosch +3

Inverse kinematics (IK) is a core operation in animation, robotics, and biomechanics: given Cartesian constraints, recover joint rotations under a known kinematic tree. In many rea…

cs.CV2026

ReConText3D: Replay-based Continual Text-to-3D Generation

Muhammad Ahmed Ullah Khan, Muhammad Haris Bin Amir, Didier Stricker +1

Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unex…

cs.CV2026

SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking

Muhammad Saif Ullah Khan, Didier Stricker

Modeling spinal motion is fundamental to understanding human biomechanics, yet remains underexplored in computer vision due to the spine's complex multi-joint kinematics and the la…

cs.CV2026

PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit

Muhammad Saif Ullah Khan, Didier Stricker

Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-i…

cs.CV2025

Towards Unconstrained 2D Pose Estimation of the Human Spine

Muhammad Saif Ullah Khan, Stephan Krauß, Didier Stricker

We present SpineTrack, the first comprehensive dataset for 2D spine pose estimation in unconstrained settings, addressing a crucial need in sports analytics, healthcare, and realis…

cs.CV2025

Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies

Shalini Sarode, Muhammad Saif Ullah Khan, Tahira Shehzadi +2

We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple ment…