jujgbbn
@trhgfb
Figuring out how handheld objects are positioned is tough but key for robots and vision systems. Using both color and depth data helps, but hand blockages and merging data types are still tricky. A new study tackles this with a smart deep learning setup. It uses a fresh voting method to blend data and a special module to handle hand-related pose guesses.
0 reply
0 recast
0 reaction