# Differential Unfolding: Efficient Unfolding Reconstruction for Video Snapshot Compressive Imaging

arXiv: https://arxiv.org/abs/2606.24153 · HTML: https://mlsanity.com/paper/2606.24153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 42 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 2 of 2)

- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Ensemble learning priors unfolding for scalable Snapshot Compressive Sensing](https://mlsanity.com/paper/2201.10419/) (2022)

## Abstract (arXiv)

While Deep Unfolding Networks (DUNs) dominate video Snapshot Compressive Imaging (SCI), they remain constrained by a uniform design philosophy. Existing methods repeatedly stack high-complexity priors with identical structures, ignoring the fact that optimization trajectories converge toward static states. This results in representation stagnation, where high-cost computations are wasted on minimal feature updates. To address this inefficiency, we present Differential Unfolding (DU), a heterogeneous framework that replaces uniform repetition with dynamic evolution. Central to DU is the Differential Evolutionary Framework (DEF), which partitions the unfolding process into two complementary roles: structural anchoring and differential evolution. In this scheme, high-parameter general stages are sparsely deployed to generate high-fidelity feature foundations. Complementing these, lightweight differential stages employ a Differential Representation Prior (DRP) to propagate and refine these foundational features through a differential mechanism. By integrating Differential Representation Attention (DRA) for evolving attention maps and a Differential Modulated FFN (DM-FFN) for feature rectification, DRP effectively models cross-stage variations with minimal overhead. By focusing computational resources on dynamic evolution rather than static redundancy, DU achieves a superior trade-off between accuracy and efficiency. Extensive experiments verify that our method establishes new state-of-the-art results while significantly slashing computational overhead. https://github.com/Muyuan-Zhang/DU