🤖 AI Summary
Traditional uniform patching in neural video implicit representations causes discontinuities at patch boundaries and global structural distortions. To address this, we propose the Structure-Preserving Patch (SPP) decoding framework. Its core innovation is a PixelUnshuffle-inspired spatial rearrangement that reorganizes video frames into structured patch sequences, enabling patch-wise implicit modeling under global consistency constraints. This mechanism facilitates end-to-end differentiable video reconstruction. Evaluated on standard benchmarks, SPP achieves PSNR gains of 1.2–2.8 dB over prior methods, outperforms existing implicit neural representation (INR) approaches in compression efficiency, and significantly enhances boundary continuity and motion coherence. To our knowledge, SPP is the first method to realize structure-aware, patch-level neural video representation—effectively bridging local patch modeling with global structural integrity.
📝 Abstract
Implicit Neural Representations (INRs) have attracted significant interest for their ability to model complex signals by mapping spatial and temporal coordinates to signal values. In the context of neural video representation, several decoding strategies have been explored to balance compactness and reconstruction quality, including pixel-wise, frame-wise, and patch-wise methods. Patch-wise decoding aims to combine the flexibility of pixel-based models with the efficiency of frame-based approaches. However, conventional uniform patch division often leads to discontinuities at patch boundaries, as independently reconstructed regions may fail to form a coherent global structure. To address this limitation, we propose a neural video representation method based on Structure-Preserving Patches (SPPs). Our approach rearranges each frame into a set of spatially structured patch frames using a PixelUnshuffle-like operation. This rearrangement maintains the spatial coherence of the original frame while enabling patch-level decoding. The network learns to predict these rearranged patch frames, which supports a global-to-local fitting strategy and mitigates degradation caused by upsampling. Experiments on standard video datasets show that the proposed method improves reconstruction quality and compression performance compared to existing INR-based video representation methods.