SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging

원문 초록

Video snapshot compressive imaging (SCI) recovers multiple frames from one spatiotemporally coded measurement. This paper proposes SpinSCI, a mask-conditioned Spatial-Temporal Spin Transformer whose Mask-Conditioned Ising Refinement Block (MC-IRB) combines attention logits and sensing information to form signed spin couplings. Finite mean-field updates gate residual feature refinement. Physics-guided initialization and final data consistency incorporate the measurement model. Compared with HiSViT$_9$, SpinSCI achieves average PSNR gains of 0.51 dB, 0.23 dB, and 0.04 dB on small-scale gray, mid-scale color, and large-scale color benchmarks, respectively, with 16.9% fewer parameters, 21.0-21.6% fewer FLOPs, 17.1-49.9% lower latency, and 62.3-63.3% lower peak memory. Relative to DU-9stg, average PSNR differs by at most 0.13 dB across these benchmarks, with 28.2-28.7% fewer FLOPs, 64.6-71.7% lower inference latency, and 30.1-35.0% lower peak memory. Qualitative comparisons on the real benchmark further show recovery of fine details and textures. Code and reference checkpoints are available at https://github.com/skethz/SpinSCI.