HandTailor: Towards High-Precision Monocular 3D Hand Recovery

by   Jun Lv, et al.

3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an optimization-based tailor module to achieve high-precision hand mesh recovery from a monocular RGB image. The proposed hand module unifies perspective projection and weak perspective projection in a single network towards accuracy-oriented and in-the-wild scenarios. The proposed tailor module then utilizes the coarsely reconstructed mesh model provided by the hand module as initialization, and iteratively optimizes an energy function to obtain better results. The tailor module is time-efficient, costs only 8ms per frame on a modern CPU. We demonstrate that HandTailor can get state-of-the-art performance on several public benchmarks, with impressive qualitative results on in-the-wild experiments.


page 2

page 3

page 4

page 5

page 6

page 8

page 9

page 10


End-to-end Hand Mesh Recovery from a Monocular RGB Image

In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackl...

Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data

We present a novel method for monocular hand shape and pose estimation a...

Synthetic Training for Monocular Human Mesh Recovery

Recovering 3D human mesh from monocular images is a popular topic in com...

Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation

3D human pose and shape recovery from a monocular RGB image is a challen...

3D Hand Shape and Pose from Images in the Wild

We present in this work the first end-to-end deep learning based method ...

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

We introduce a simple and effective network architecture for monocular 3...

Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration

Recent years have witnessed significant progress in 3D hand mesh recover...