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.
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...
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
arXiv:2608.20910v1 Announce Type: new Abstract: With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place edi...
arXiv:2608.27123v1 Announce Type: new Abstract: Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, dire...
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
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.
arXiv:2606. 09056v1 Announce Type: cross Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths.
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
arXiv:2601.16296v3 Announce Type: replace-cross Abstract: Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative....
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...