SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/skethz/SpinSCI
Terminology
Sources
- Adam: A Method for Stochastic Optimization
- Mixed Precision Training
- On the difficulty of training Recurrent Neural Networks
- The 2017 DAVIS Challenge on Video Object Segmentation
- Differential Unfolding: Efficient Reconstruction for Video Snapshot Compressive Imaging
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs