AIAny
Icon for item

LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models

Recovers and predicts RGB video from sparse event-camera streams by fine-tuning pre-trained video diffusion priors; jointly addresses reconstruction, long-horizon prediction, and bidirectional frame interpolation with mechanisms to reduce temporal drift and enforce interpolation consistency.

Introduction

LongE2V targets a concrete bottleneck in event-based vision: turning highly sparse, asynchronous event streams into stable, photorealistic video over long time horizons. Event cameras give superior temporal resolution but produce very different data than frame cameras; prior regression methods blur textures and prior generative approaches tend to drift over long sequences. LongE2V leverages a pre-trained video diffusion foundation model and adds targeted adaptations so a single approach can reconstruct, predict, and interpolate long event-driven video with strong temporal coherence.

Key Findings
  • Fine-tuning a foundational video diffusion prior yields high data efficiency and perceptual quality compared with training from scratch, so you get better-looking reconstructions with less task-specific data.
  • Autoregressive Unrolling + Adaptive Context Switching mitigates long-term temporal drift, so the model maintains consistency over much longer sequences than prior generative methods.
  • Reencoding Alignment with Cross Residual Correction enforces precise bidirectional consistency for frame interpolation, so interpolated frames align closely with both past and future contexts.
  • Event Voxel Density Augmentation improves robustness across sensor resolutions, so the same model generalizes better zero-shot to different event-camera settings and datasets.
Who it's for — tradeoffs

Great fit if you work on event-based vision, video generation, or multi-task video modeling and need perceptually high-quality reconstruction, long-term prediction, or consistent bidirectional interpolation from event streams. It is less suitable if you require ultra-low-latency on-device inference or strictly deterministic, pixel-perfect reconstruction under extreme sensor noise; the approach depends on a pretrained video diffusion backbone and nontrivial fine-tuning compute. In short, use LongE2V when perceptual fidelity and temporal coherence across long sequences matter more than minimal latency or purely deterministic outputs.

Information

  • Websitearxiv.org
  • OrganizationsNational Yang Ming Chiao Tung UniversityTaiwan
  • AuthorsCheng-De Fan, Chun-Wei Tuan Mu, Chen-Wei Chang, Chin-Yang Lin, Kun-Ru Wu, Yu-Chee Tseng, Yu-Lun Liu
  • Published date2026/07/09

More Items

Provides a diagnostic suite that audits video-understanding benchmarks to find samples solvable without visual or temporal input, filters those shortcuts, and produces a distilled video-native testbed that reveals major capability gaps in current Video-LLMs.

Reduces object-driven shortcut learning in zero-shot compositional action recognition by enforcing temporal verb cues and regularizing against frequent object-verb co-occurrence priors. Proposes RCORE with Co-occurrence Prior Regularization (treats frequent co-occurrences as hard negatives) and Temporal Order Regularization. Evaluated on Sth-com and EK100-com with improved compositional generalization.

Generates real-time, infinite-length interactive videos of voice-controllable digital characters — 540p at up to 42 FPS on consumer GPUs. Uses TurboDiffusion and TurboServe to maintain temporal coherence without blur or drift, and accepts custom person, anime, or pet images plus selectable voice tones.