Search papers, labs, and topics across Lattice.
This paper introduces GTF, a novel omnidirectional EPI Transformer for light field super-resolution that explicitly models horizontal, vertical, 45-degree, and 135-degree EPIs. By combining directional EPI processing, MacPI-based prior injection, adaptive directional fusion, and a topology-preserving feed-forward network, GTF better exploits LF geometry. Results on five standard LF SR benchmarks and the NTIRE 2026 Light Field Image Super-Resolution Challenge demonstrate the effectiveness of the approach, achieving state-of-the-art performance and ranking highly in the challenge.
Overlooked diagonal epipolar geometry holds the key to boosting light field super-resolution, as demonstrated by a new omnidirectional EPI Transformer.
Light field (LF) image super-resolution benefits from Epipolar Plane Images (EPIs), whose line slopes explicitly encode disparity. However, existing Transformer-based LF SR methods mainly attend to horizontal and vertical EPIs, leaving diagonal epipolar geometry underexplored. We present GTF, an omnidirectional EPI Transformer that explicitly models horizontal, vertical, 45-degree, and 135-degree EPIs within a unified reconstruction framework. GTF combines directional EPI processing, MacPI-based prior injection, adaptive directional fusion, and a topology-preserving feed-forward network to better exploit LF geometry. For the NTIRE 2026 fidelity tracks, we use GTF as the main model, while a lightweight GTF-Tiny variant targets the efficiency track. On five standard LF SR benchmarks covering both real-captured and synthetic scenes, GTF reaches 32.78 dB without inference-time enhancement, and stronger inference settings with EPSW and test-time augmentation further improve performance. Under the NTIRE 2026 efficiency constraint, GTF-Tiny attains 32.57 dB with only 0.915M parameters and 19.81 GFLOPs. In the NTIRE 2026 Light Field Image Super-Resolution Challenge, our submissions rank 3rd on Track 1 and Track 3 and 4th on Track 2. Architecture-evolution, channel-width, and inference analyses further support the effectiveness of diagonal EPI modeling, directional fusion, and the lightweight design.
