Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding
This work addresses a specific problem in computer vision for applications like human-computer interaction or AR/VR, but it is incremental as it builds on existing 3D hand mesh recovery methods by focusing on blurry images.
The paper tackles the problem of recovering 3D hand mesh sequences from single blurry images, which is challenging due to motion blur from hand movements, by introducing a new dataset BlurHand and a baseline network BlurHandNet that outputs a sequence instead of a static mesh, resulting in more robust performance on blurry images with good generalization to in-the-wild images.
Hands, one of the most dynamic parts of our body, suffer from blur due to their active movements. However, previous 3D hand mesh recovery methods have mainly focused on sharp hand images rather than considering blur due to the absence of datasets providing blurry hand images. We first present a novel dataset BlurHand, which contains blurry hand images with 3D groundtruths. The BlurHand is constructed by synthesizing motion blur from sequential sharp hand images, imitating realistic and natural motion blurs. In addition to the new dataset, we propose BlurHandNet, a baseline network for accurate 3D hand mesh recovery from a blurry hand image. Our BlurHandNet unfolds a blurry input image to a 3D hand mesh sequence to utilize temporal information in the blurry input image, while previous works output a static single hand mesh. We demonstrate the usefulness of BlurHand for the 3D hand mesh recovery from blurry images in our experiments. The proposed BlurHandNet produces much more robust results on blurry images while generalizing well to in-the-wild images. The training codes and BlurHand dataset are available at https://github.com/JaehaKim97/BlurHand_RELEASE.