arXiv:2609.36598v1 Announce Type: new Abstract: A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is un...
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.
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.
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.
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...
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
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.
ClearText-Video (CTVid) is a large-scale, scene-text-aware benchmark that examines text-centric video understanding under varying quality conditions. It comprises 4,639 real-world egocentric videos, over 550,000 frames, 1.6 million human-verified scene-text annotations, and more than 220,000 spatial/temporal question–answer pairs in Chinese and English. For each high-quality video, CTVid provides matched degraded- and restored-quality variants, enabling studies of Text-Centric Video Restoration and Multi-Quality VideoQA, and revealing that visual enhancement does not always improve textual fidelity or downstream reasoning.
arXiv:2609.14899v1 Announce Type: new Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent...
WanPE is a 397‑B parameter prompt‑enhancement model that learns director‑level cinematic planning from 1.05 M real‑world videos. It generates shot‑level cinematic plans through video‑grounded reverse construction and uses Semantic‑Consistency GRPO (SC‑GRPO) to maintain user intent across shots and time. In evaluations, WanPE improves human preference over raw prompts by up to 50.86 points for 30‑second videos and outperforms commercial offerings for shorter durations.
arXiv:2607. 19895v1 Announce Type: cross Abstract: Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion.
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.