SemantiScene-Edit is a video editing system that uses a multimodal encoder and a pretrained video diffusion transformer to follow natural‑language instructions while preserving the source video’s appearance and temporal structure. The encoder processes source frames and the instruction together, sending semantic queries to the generator via a trainable connector and cross‑attention. A dual‑path visual route concatenates source‑video latents with noisy target latents to provide dense spatial and temporal information, and the model is trained with flow matching and a three‑stage curriculum on over 1.2 million instruction‑conditioned records, with a 100‑case benchmark for evaluation.
By Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu, Shengrong Gu, Liang Li, Qian Wang, Junlan Feng, Ying Tai, Jian Yang, Zili Yi
The paper introduces vid2vid-long, a video-to-video translation method that uses explicit patch-level correspondences between input frames to guide generation. By retrieving and conditioning on previously generated outputs in matching regions, the approach maintains long-range temporal consistency without sacrificing real-time performance. Experiments show consistent improvements over recent models while preserving generation quality.
By Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Srinivasa Narasimhan, Eli Shechtman, Yotam Nitzan
CameraEditor is a new framework that transforms camera-controlled image editing into a temporal sequence prediction problem. By using video diffusion models, it incorporates a geometric perception module and dynamic reference routing to create precise visual references through dynamic panorama cropping. The method also inserts intermediate transition frames to handle large perspective shifts, maintaining content identity and spatial coherence, and is evaluated on a dataset of 5,760 instances with a benchmark of 462 test cases, achieving state‑of‑the‑art performance.
By Xin Shen, Chengyou Jia, Keshuo Xing, Zifeng Zhu, Changliang Xia, Bowen Ping, Zhuohang Dang, Hangwei Qian, Minnan Luo
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.
By Habin Lim, Gyeong-Moon Park
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
By Ziyang Mai, Yu-Wing Tai
The paper introduces DSG‑GI, a method that adapts pretrained latent video diffusion models for generative inbetweening by using Destination‑Conditioned Adaptation and Semantic‑Geometric Alignment. Destination‑Conditioned Adaptation treats the target frame as the sequence’s endpoint, providing progressive guidance along the generated trajectory. Semantic‑Geometric Alignment aligns token‑wise spatio‑temporal geometry of backbone features with a frozen video encoder and enforces a flow‑matching latent flow constraint near the data endpoint, thereby improving temporal stability, target‑frame faithfulness, and perceptual quality on large‑motion benchmarks.
By Zhiyu Xu (Tianjin University), Wei Shang (Singapore Management University), Yushen Xu (Tianjin University), Wenwen Li (Tianjin Medical University), Zhiyan Xu (Southeast University), Pengfei Zhu (Tianjin University), Dongwei Ren (Tianjin University)
arXiv:2609.39157v1 Announce Type: new
Abstract: Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generat...
By Songhe Wang, Lifu Wei, Shuolin Xu, Charles A. Kamhoua, David Miller
WorldForge V2 introduces a training‑free guidance framework that refines video diffusion outputs along a target camera path using warped references and optical‑flow‑identified latent channels for selective guidance. It employs a dual‑path strategy to correct artifacts, a v‑cache to reduce refinement cost, and Trajectory LoRA adapters trained in two stages to focus on trajectory‑responsive network blocks. The approach achieves state‑of‑the‑art generation quality and trajectory accuracy with minimal training data, enabling reliable camera control across unseen scenes.
By Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Joey Tianyi Zhou, Chi Zhang
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
By Haengbok Chung
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.
By Leigang Qu, Feng Cheng, Ziyan Yang, Bangbang Yang, Zhaoyang Huang, Wei Chow, Yicong Li, Wenjie Wang, Tat-Seng Chua, Yan Zeng
arXiv:2610.23856v1 Announce Type: new
Abstract: Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smoot...
By Weijie Lyu, Tiancheng Shen, Jason Li, Yujing Wang, Xiaoyuan Wang, Haobo Yuan, Yizhou Zhao, Ming-Hsuan Yang
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.
By Sicong Yang, Ruihuan Yang, Jian Lu, Jianfei Yuan, Xiaodong Cun, Xiuli Bi