4 papers
GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
Pradyumna YM, Yuxuan Xue, Yue Chen +3
Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are…
InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement
Nikita Kister, Pradyumna YM, István Sárándi +3
Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, yet such data is scarce. Real-…
Are Pose Estimators Ready for the Open World? STAGE: A GenAI Toolkit for Auditing 3D Human Pose Estimators
Nikita Kister, István Sárándi, Jiayi Wang +2
For safety-critical applications, it is crucial to audit 3D human pose estimators before deployment. Will the system break down if the weather or the clothing changes? Is it robust…
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
István Sárándi, Gerard Pons-Moll
With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm. A key to successfully exploiting data scal…