Command Palette
Search for a command to run...
Welter Michael
Abstract
Deep learning has been impressively successful in the last decade inpredicting human head poses from monocular images. However, for in-the-wildinputs the research community relies predominantly on a single training set,300W-LP, of semisynthetic nature without many alternatives. This paper focuseson gradual extension and improvement of the data to explore the performanceachievable with augmentation and synthesis strategies further. Modeling-wise anovel multitask head/loss design which includes uncertainty estimation isproposed. Overall, the thus obtained models are small, efficient, suitable forfull 6 DoF pose estimation, and exhibit very competitive accuracy.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| face-alignment-on-aflw2000-3d | OpNet | Balanced NME (2D Sparse Alignment): 3.55% |
| head-pose-estimation-on-aflw2000 | OpNet | Geodesic Error (GE): 5.23 MAE: 3.15 |
| head-pose-estimation-on-biwi | OpNet | Geodesic Error (GE): 7.01 Geodesic Error - aligned (GE): 4.72 MAE (trained with other data): 3.57 MAE-aligned (trained with other data): 2.65 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.