Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

Chunhua Shen, Zhongang Cai, Yanjun Wang, Wenjia Wang, Lei Yang, Taku Komura, Haiyi Mei, Yongtao Ge, Qingping Sun

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

wenjiawang0312/zolly — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

a) Input image (b) SPEC (c) Our results (d) Input image (e) SPEC (f) Our results FoV = 50°z = 1.28m FoV = 79°z = 0.94m Figure 1: Close-up photography can make it difficult to discern 3D human pose in perspective-distorted images, while stateof-the-art methods often struggle with weak-perspective camera models or inaccurate focal length estimates. Our method overcomes these challenges, accurately recovering 3D human mesh from an approximate distance for fine-grained reconstruction. We could thus get focal length by our proposed approach.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.13796")
get_code_for_paper("2303.13796")
have("2303.13796")

Connect an agent — have() is free.