Wanli Ouyang, Limin Wang, Zhenan Sun, Yebin Liu, Xinchi Zhou, Hongwen Zhang, Yating Tian
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images. By directly mapping raw pixels to model parameters, these methods can produce parametric models in a feed-forward manner via neural networks. However, minor deviation in parameters may lead to noticeable misalignment between the estimated meshes and image evidences. To address this issue, we propose a Pyramidal Mesh Alignment Feedback (PyMAF) loop to leverage a feature pyramid and rectify the predicted parameters explicitly based on the mesh-image alignment status in our deep regressor. In PyMAF, given the currently predicted parameters, mesh-aligned evidences will be extracted from finerresolution features accordingly and fed back for parameter rectification. To reduce noise and enhance the reliability of these evidences, an auxiliary pixel-wise supervision is imposed on the feature encoder, which provides mesh-image correspondence guidance for our network to preserve the most related information in spatial features. The efficacy of our approach is validated on several benchmarks, including Human3.6M, 3DPW, LSP, and COCO, where experimental results show that our approach consistently improves the mesh-image alignment of the reconstruction. The project page with code and video results can be found at https://hongwenzhang.github.io/pymaf.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.16507")
get_code_for_paper("2103.16507")
have("2103.16507")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.16507.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.16507)
Connect an agent — have() is free.