arXiv:2610.20137v1 Announce Type: new Abstract: Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction....
arXiv:2607. 24560v1 Announce Type: cross Abstract: We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D.
We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the post-event continuation.
Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second late...
The paper introduces Anchor-based Video Editing (AVE), a two-stage framework that converts a powerful image editor into a video editor by first editing keyframes and then propagating those edits across time using a motion-guided image-to-video diffusion model. AVE treats edited keyframes as fixed anchors, leveraging the strengths of modern image editors while avoiding costly end-to-end video training. Experiments on IVEBench and VIE-Bench demonstrate strong performance in instruction following, temporal consistency, and content fidelity, and ablations show that video quality correlates with the underlying image editor’s performance.
Memory-V2V is a memory‑augmented video‑to‑video diffusion framework designed to improve cross‑turn consistency in multi‑turn video editing. It stores previous outputs in an external memory, retrieves relevant edits, and incorporates them via relevance‑aware tokenization and adaptive compression, allowing scalable conditioning without linear computational growth. Experiments on iterative video novel view synthesis and text‑guided long video editing show that Memory‑V2V enhances consistency while preserving visual quality and outperforming strong baselines with modest overhead.
Instruction-Based Video Editing by Repurposing an Image Editing Model demonstrates that a strong image‑editing model can be adapted to edit videos by operating on video‑VAE latents. The authors tile latent frames into a large virtual image, reuse the editor’s positional encoding, and bridge latent spaces with lightweight projections, fine‑tuning on Ditto‑1M editing triplets. Their experiments show that per‑frame video latents are close enough to the image domain that mature image‑editing priors transfer with minimal adaptation.
EditaLive! is a new real‑time framework for character video editing in live streaming, built on a pretrained image animation model (Wan‑Animate) that separates appearance from motion. It uses the CharEdit‑50K dataset for reference‑frame editing and video reconstruction, and adapts the model from offline bidirectional to causal streaming generation. A self‑rollout distillation strategy compresses the model into a two‑step sampler, employing fixed RoPE, alignment forcing, and first‑frame preserved sparse attention to reduce appearance drift and achieve low‑latency inference while preserving facial expressions.
The paper introduces Sora100K, a dataset that captures AI‑Native video creation workflows as structured trajectories rather than isolated clips. It categorizes trajectories into text‑to‑video generation roots, single‑turn editing edges, and multi‑turn editing sequences, annotating each with semantic and operation labels via a VLM. A rigorous construction pipeline ensures accurate source‑to‑edit lineage and intermediate states, and lightweight adaptation on LTX‑2 models demonstrates improved visual quality, multi‑shot generation, and cross‑shot consistency, though multi‑turn editing remains challenging.
arXiv:2607.18227v2 Announce Type: replace Abstract: In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and imag...
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration.
EditStream is a unified DiT‑based framework that supports a wide range of interactive video tasks—Text‑to‑Video, Image‑to‑Video, Video‑to‑Video, Editing Propagation, Reference‑guided Video Editing, and Camera Pose Change—within a single system. It achieves fast, few‑step autoregressive generation by applying a two‑stage distillation process that combines Velocity Moment Matching with autoregressive unrolling, thereby preserving motion quality and temporal stability. The approach aims to make high‑quality diffusion‑based video models practical for real‑time creative workflows.