Updating Depth-aware Feature in the Feedback Loop for Human Mesh Recovery

Recently, depth ambiguity reduction has made significant progress in monocular human mesh reconstruction. However, regression-based methods struggle to perceive minor depth deviations due to insufficiently exploited monocular cues, such as linear perspective, shadows, and pose priors of the given image. To tackle this limitation, we propose a Depth-aware Updated Feature Feedback (DAUFF) loop to iteratively exploit spatial information from rendered images. Specifically, the normalized depth and dense correspondence images rendered from the ground truth human meshes are adopted as auxiliary supervision for more reliable and adequate cues. Moreover, we also use dense correspondences for feature update to improve the adaptability to new predictions in the loop. Remarkably, dense correspondences can facilitate the rectification of parameters by providing a fine-grained perception of the current prediction. Extensive quantitative comparison on standard benchmarks shows that DAUFF achieves better-aligned reconstruction results than existing approaches. The dataset and codes will be available on the project homepage: https://github.com/github1838/DAUFF.