Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Gayoung, Kim, Junho, Kim, Jin-Hwa, Kim, Junmo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911287673356288
author Lee, Gayoung
Kim, Junho
Kim, Jin-Hwa
Kim, Junmo
author_facet Lee, Gayoung
Kim, Junho
Kim, Jin-Hwa
Kim, Junmo
contents Understanding reflection remains a long-standing challenge in 3D reconstruction due to the entanglement of appearance and geometry under view-dependent reflections. In this work, we present the Pygmalion Effect in Vision, a novel framework that metaphorically "sculpts" reflective objects into clay-like forms through image-to-clay translation. Inspired by the myth of Pygmalion, our method learns to suppress specular cues while preserving intrinsic geometric consistency, enabling robust reconstruction from multi-view images containing complex reflections. Specifically, we introduce a dual-branch network in which a BRDF-based reflective branch is complemented by a clay-guided branch that stabilizes geometry and refines surface normals. The two branches are trained jointly using the synthesized clay-like images, which provide a neutral, reflection-free supervision signal that complements the reflective views. Experiments on both synthetic and real datasets demonstrate substantial improvement in normal accuracy and mesh completeness over existing reflection-handling methods. Beyond technical gains, our framework reveals that seeing by unshining, translating radiance into neutrality, can serve as a powerful inductive bias for reflective object geometry learning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
Lee, Gayoung
Kim, Junho
Kim, Jin-Hwa
Kim, Junmo
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Understanding reflection remains a long-standing challenge in 3D reconstruction due to the entanglement of appearance and geometry under view-dependent reflections. In this work, we present the Pygmalion Effect in Vision, a novel framework that metaphorically "sculpts" reflective objects into clay-like forms through image-to-clay translation. Inspired by the myth of Pygmalion, our method learns to suppress specular cues while preserving intrinsic geometric consistency, enabling robust reconstruction from multi-view images containing complex reflections. Specifically, we introduce a dual-branch network in which a BRDF-based reflective branch is complemented by a clay-guided branch that stabilizes geometry and refines surface normals. The two branches are trained jointly using the synthesized clay-like images, which provide a neutral, reflection-free supervision signal that complements the reflective views. Experiments on both synthetic and real datasets demonstrate substantial improvement in normal accuracy and mesh completeness over existing reflection-handling methods. Beyond technical gains, our framework reveals that seeing by unshining, translating radiance into neutrality, can serve as a powerful inductive bias for reflective object geometry learning.
title Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2511.21098