Andrew Chalmers

2 accepted papers

2026

SE360: Semantic Edit in 360° Panoramas via Hierarchical Data Construction

Haoyi Zhong, Fang-Lue Zhang, Andrew Chalmers, Taehyun Rhee

AAAI 2026technical

While instruction-based image editing is emerging, extending it to 360° panorama introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views. To address these limitations, we propose SE360, a novel framework for

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Deep Portrait Delighting

Joshua Weir, Junhong Zhao, Andrew Chalmers, Taehyun Rhee

ECCV 2022poster

"We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize high-frequency shading features; soft-shadow loss, which im…

Cited by 14 Source ↗PDF ↗Scholar ↗