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...
VINCIE‑NExT is a unified framework that transfers image editing capabilities to video editing by using in‑context visual demonstrations. It decomposes video editing into a chain of sub‑tasks (Video → Image → Image → Video), routing editing intent through the image domain and enabling joint training from heterogeneous image and video data under a single diffusion objective. The method introduces a novel position encoding to link image demonstrations and video frames, allowing pixel‑faithful appearance propagation, and supports test‑time scaling through progressive diffusion stages.
RefVideo-6M is a new large-scale reference-guided editing dataset that includes 5 million video editing samples and 1 million image editing samples, each paired with about 6 million visual references. The dataset is constructed to avoid artifacts by using real, artifact‑free videos as targets and filtering input conditions with multiple editing experts, thereby providing reliable supervision. It enables models to learn fine‑grained visual correspondence beyond text‑only instructions and supports the training of a reference‑guided video editing model, Ref‑MoT, which shows improved visual quality, controllability, and reference consistency.
Edit‑VAR is a training‑free, inversion‑free framework that uses a pretrained visual autoregressive video model for text‑guided video editing. It encodes the source video into multi‑scale discrete tokens and applies probability‑guided conditional token replacement, attention‑guided token‑wise and scale‑aware modulation, and scale‑decoupled generation to preserve source appearance while enabling precise edits. The method also includes residual‑guided token pruning to reduce inference cost, and experimental results show it outperforms existing training‑free video editing methods in fidelity, source preservation, temporal coherence, and efficiency.
arXiv:2608.17566v2 Announce Type: replace Abstract: The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing...
Bernini proposes a unified framework that separates semantic planning and pixel rendering for video generation and editing. An MLLM-based planner predicts target semantics in ViT embedding space, while a DiT-based renderer synthesizes pixels conditioned on this plan, text features, and source VAE features for editing. The approach introduces Segment-Aware 3D Rotary Positional Embedding and chain-of-thought reasoning, achieving state‑of‑the‑art performance on diverse video benchmarks.
VIDiff is a unified foundation model that uses diffusion techniques to perform a broad range of video tasks, including both understanding tasks like language‑guided video object segmentation and generative tasks such as video editing and enhancement. Unlike prior methods that focus on short clips and require time‑consuming tuning, VIDiff can edit and translate videos within seconds based on user instructions and employs an iterative auto‑regressive approach to maintain consistency in long‑form videos. The authors demonstrate convincing generative results across diverse input videos and written instructions, supported by qualitative and quantitative evidence.
OmniEdit-Bench introduces a comprehensive benchmark for instruction-based video editing (IVE), addressing limitations of existing datasets by covering spatial, temporal, audio, and reference-based editing tasks and distinguishing explicit from implicit instructions. The evaluation framework assesses editing quality across accuracy, preservation, realism, and consistency, using human judgments and vision-language models, and incorporates an accuracy-aware penalty to ensure instruction fidelity. Experiments reveal that current IVE models perform poorly, highlighting the need for improved methods.
Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptual gap, we propose Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair.
CoinVE-200K is a large, high‑quality dataset for compositional instruction‑guided video editing, featuring 1080p video‑editing pairs up to 201 frames long and containing 2–5 atomic editing operations per sample. The dataset covers diverse editing intents—targeting humans, objects, and backgrounds with addition, removal, modification, and stylization—while ensuring instruction faithfulness, visual quality, temporal consistency, and compositional diversity through a careful generation and filtering pipeline. CoinVE-Bench benchmarks these capabilities, and CoinVE-Edit, a 22B model built on Wan2.1‑T2V‑14B and Qwen3‑VL‑8B‑Instruct, demonstrates strong performance in instruction following, compositional editing accuracy, visual quality, and temporal consistency.
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:2610.22744v1 Announce Type: new Abstract: Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), v...