AI Paper Atlas

Research map / Image generation / Editing and style transfer

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

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

AAAI 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on SE360-HF after SE360-Base pre-training (two-stage) (ablation)SE360 · PanoEval object additionCSpers (CLIP score): 27.965 -> 29.354Improved
fine-tune on SE360-HF after SE360-Base for object removal (ablation)SE360 · PanoEval object removalFAED: 0.498 -> 0.314Improved
train only on SE360-HF instead of two-stage (ablation)SE360 · PanoEval object removalPSNR: 26.394 -> 19.419Hurt
train only on SE360-HF instead of two-stage (ablation)SE360 · PanoEval object additionLPIPS: 0.076 -> 0.171Hurt
fine-tune on SE360-HF (remove artifact overfitting) when evaluated on LaMa-artifact-containing data (ablation)SE360 · PanoEval object additionCSpers (CLIP score): 29.377 -> 29.354Hurt
train only on SE360-Base (LaMa-erased data) instead of adding HF refinement (ablation)SE360 · PanoEval object removalCS-Nopers: 73.143 -> 73.055Hurt
SE360 versus Step1X-Edit on removal reconstruction metricsSE360 · PanoEval object removalPSNR: SE360 26.394 vs Step1X-Edit 28.471Hurt
SE360 versus Flux.1 Kontext dev on addition semantic scoreSE360 · PanoEval object additionCSpers (CLIP score): 29.295 -> 29.354No clear effect
SE360 versus top-performing models in user studySE360 · User study consistencyLikert score: 2.91 -> 4.47 (vs Flux.1 Kontext dev)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy