AI Paper Atlas

Research map / Image generation / Image restoration

Image Stitching in Adverse Condition: A Bidirectional-Consistency Learning Framework and Benchmark

Zengxi Zhang, Junchen Ge, Zhiying Jiang, Miao Zhang, Jinyuan Liu

NeurIPS 2025 · Image generation › Image restoration · approach: Image harmonization and color transformation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a bidirectional-consistency learning framework for deep image stitching robust to adverse conditions (weather, illumination, dynamic motion), along with a benchmark for this setting.

Problem

Deep learning image stitching degrades on real-world adverse conditions such as complex weather, illumination variation, and dynamic scene motion, causing significant misalignment.

Approach

An adverse-condition-tolerant stitching framework that uses bidirectional consistency learning, plus a benchmark dataset covering adverse conditions. Details beyond the abstract are not available.

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