9 papers
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…
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…
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…
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…
Towards Unconstrained 2D Pose Estimation of the Human Spine
Muhammad Saif Ullah Khan, Stephan KrauÃ, 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…
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…