OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation
Xiaoan Zhu, Yue Zhao, Tianyang Hu, Jiaming Guo, Yulan Zeng, Renjing Pei, Fenglong Song, Huajun Feng
Abstract
Dual-camera smartphones suffer from geometric and photometric inconsistencies during zoom transitions, primarily due to disparities in intrinsic/extrinsic parameters and divergent image processing pipelines between the two cameras. Existing interpolation methods struggle to effectively address this issue, constrained by the lack of ground-truth datasets and motion ambiguity in dynamic scenarios. To overcome these challenges, we propose OmniZoom, a universal plug-and-play paradigm for cross-device smooth zoom interpolation. Specifically, we present a novel cross-device virtual data generation method utilizing 3D Gaussian Splat-ting. This method tackles data scarcity by decoupling geometric features via spatial transition modeling and correcting photometric variations with dynamic color adaptation. It is further enhanced by cross-domain consistency learning for device-agnostic semantic alignment. Additionally, we introduce a plug-and-play 3D Trajectory Progress Ratio (3D-TPR) framework that surmounts 2D spatial limitations. As components of our framework, a texture-focus strategy is introduced for high-frequency detail preservation, incorporating mask penalty constraints to suppress interpolation artifacts. Our pipeline exhibits broad compatibility with diverse interpolation methods and achieves good performance across multiple public benchmarks. Real-world evaluations on various smartphone platforms also reveal significant quality improvements after finetuning on our synthetic data, which underscores the robustness and practical effectiveness of our approach for cross-device zoom applications.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
- Exploring CLIP for Assessing the Look and Feel of Images cites MUSIQ: Multi-scale Image Quality Transformer
Builds on16
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- MUSIQ: Multi-scale Image Quality TransformerJunjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar et al.ICCV 2021 · 1,325 citations
- Exploring CLIP for Assessing the Look and Feel of ImagesJianyi Wang, Kelvin C. K. Chan, Chen Change LoyAAAI 2023 · 1,208 citations
- DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction ModelYinghao Xu, Hao Tan, Fujun Luan, Sai Bi et al.ICLR 2024 · 234 citations
Related papers
- Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional ImagesChangha Shin, Woong Oh Cho, Seon Joo KimICCV 2025 · 5 citations
- TriGS: Tri-consistency 3D Gaussian Splatting from Sparse and Unposed ViewsChi Huang, Qi Zhang, Qian Zhang, Nan Li et al.ACM MM 2025 · 3 citations
- Cross-Spectral Gaussian Splatting with Spatial Occupancy ConsistencyHaipeng Guo, Huanyu Liu, Jiazheng Wen, Junbao LiAAAI 2025 · 1 citation
- OminiMAG-SLAM : Unified Online Dual Graph Optimization for Multi-Agent Gaussian SLAMLeqian Ding, Caibo Li, Yu Guo, Fei WangCVPR Findings 2026
- Omnidirectional 3D Scene Reconstruction from Single ImageRen Yang, Jiahao Li, Yan LuNeurIPS 2025
