Skip to content
Preprint

LiveView: Real-Time Camera-Controlled Re-filming of Streaming Videos

You-Can Xu Xin-Jie Huang Jia-Xin Shi Hengye Lyu Zhen Wang Jun Xiao Long Chen
Nov 2026 · 0 citations
Computer Science

Abstract

Real-time camera-controlled video re-filming aims to synthesize target views from a streaming source video under online user-specified camera trajectories. This task poses two key challenges: maintaining synchronization and content consistency across views, and achieving low-latency rendering with long-horizon stability. Existing approaches are predominantly designed for offline full-sequence processing and rely on bidirectional attention or costly depth-based geometric preprocessing, making them unsuitable for low-latency streaming scenarios. To address these limitations, we develop a teacher-to-student framework that distills a high-fidelity bidirectional re-filming teacher into a few-step causal autoregressive student. We introduce Cross-Frame Injection to interleave each incoming source frame with its synchronized target latent, thereby establishing direct cross-view correspondence and improving content consistency. To ensure stable long-horizon generation, we further propose Shared Relative RoPE, which bounds temporal indices within the pretrained range, and Cycle Streaming Tuning, which exposes the student to extended cyclic trajectories during streaming training. These designs enable low-latency online video re-filming with precise camera control and sustained spatiotemporal consistency over long streaming rollouts.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.