Overview

Image-to-video generation studies how to turn a still image into a moving clip while preserving the subject, scene, and visual style. Most systems extend pretrained video diffusion models, using temporal attention, lightweight adapters, or controls such as poses, trajectories, masks, depth, and camera paths; some add 3D geometry or physics simulation to guide motion. Training-free prompt refinement and inference-time search offer alternative ways to improve control, while distillation and sparse attention target faster generation. Evaluation increasingly tests motion adherence, identity and scene consistency, physical plausibility, and safety, but realistic appearance and smooth motion still do not guarantee correct physics or precise control.

Latest papers

CardsList

102 papers11 papers in the last four weeks, down 8% on the four weeks before. 0.1% of all new papers.

  1. Not All Layers Are Equal in Image-to-Video Transfer

    Nov 8, 2026Thinesh Thiyakesan Ponbagavathi, Constantin Seibold, Alina RoitbergFine-Grained Action UnderstandingVision Foundation Model Adaptation

  2. DualCast: Dual-Image Conditioned Diffusion Transformers for Digital Human E-Commerce Video Generation

    Nov 4, 2026Lifan Jiang, Yibo Zhao, Senlin Cheng +6Video GenerationImage-to-Video Generation

  3. Synthetic Realities: Evaluating Human Ability to Distinguish AIGenerated Videos from Real Footage

    Nov 1, 2026Danyal Sarfraz, Raja Mubashar Karim, KwanMyung KimVideo Generation EvaluationSynthetic Video Detection Benchmarks

  4. IMPACT: Image-Conditioned Motion with Physics-Aware Collision and Trajectory Guidance for Video Generation

    Nov 1, 2026Shiwei Yang, Yunlong Yu, Zhao Wang +1Physical Consistency in Video GenerationImage-to-Video Generation

  5. GeoFlip Preview: Benchmarking Geometry-Sensitive Physics in Video Generation

    Oct 30, 2026Yuqi Li, Junming Liu, Bowen Hu +5Physical Consistency in Video GenerationGeometric Consistency in Video Generation

  6. Edited Endpoints as Partial Goals for Image-to-Video Generation

    Oct 29, 2026Sihyun Kim, Sanghyun Jo, Kyungsu KimImage-to-Video GenerationControllable Video Generation

  7. PhaseBreak: Proactive Temporal Protection against Unauthorized Image-to-Video Animation

    Oct 20, 2026Jiashu Zhang, Xuanyou Li, Qixin ZhangAdversarial Attacks on Diffusion ModelsImage-to-Video Generation

  8. Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning

    Oct 19, 2026Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou +3Agentic Video GenerationImage-to-Video Generation

  9. Wan-Alpha++: Animating a Single RGBA Asset into Controllable Transparent Video Effects

    Oct 19, 2026Haotian Dong, Xin Wang, Wenjing Wang +7Controllable Video GenerationVideo Diffusion Models

  10. TextVBench: Evaluating Text Rendering and Preservation in Video Generation

    Oct 9, 2026Ruiqiang Zhang, Hengyi Wang, Chang Liu +3Video Generation EvaluationT2V Generation

  11. LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse

    Oct 9, 2026Boheng Li, Yueming Xing, Yiming Li +2Image-to-Video GenerationAdversarial Examples

  12. Golden Anchor for Video Generation

    Oct 9, 2026Jinyuan Xu, Shitong Shao, Lichen Bai +4Image-to-Video GenerationT2I Generation

  13. Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife

    Oct 4, 2026Yuzhuo Li, Di Zhao, Xinyu Zhang +2Image-to-Video GenerationIdentity-Preserving Video Generation

  14. How Does Geometry Enter Generated Motion?

    Oct 4, 2026Weihan Li, Junhao Wu, Yuhan Song +2Physical Consistency in Video GenerationImage-to-Video Generation

  15. VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation

    Oct 2, 2026Yutong Wang, Xingtong Ge, Enhuai Liu +6Diffusion Model DistillationFew-Step Diffusion Sampling

  16. MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation

    Oct 1, 2026Yiwen Zhang, Haocheng Xi, Michael Tian-Yue Liu +4Image-to-Video GenerationLong-Horizon Video Generation

  17. PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video

    Oct 1, 2026Junseong Shin, Hyeonsu Jo, Daehyun Kim +1Image-to-Video GenerationImage Deblurring

  18. MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation

    Sep 30, 2026Ruiqi Li, Xuanyi Liu, Sijia Li +9Image-to-Video GenerationTheory of Mind

  19. PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

    Sep 15, 2026Chuhao Chen, Peter Wonka, Chaoyang Wang +4Physical Consistency in Video GenerationImage-to-Video Generation

  20. The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation

    Sep 7, 2026Peng Li, Qianqian Xu, Yangbangyan Jiang +2Image-to-Video GenerationMultimodal Jailbreak Attacks

  21. PhysWeep: Does a Video Generator Realize the Physics You Ask For?

    Sep 5, 2026Rasul Khanbayov, Hasan KurbanPhysical Consistency in Video GenerationImage-to-Video Generation

  22. TempJail: Temporal Jailbreak Attacks against Image-to-Video Generation Models

    Aug 27, 2026Qi Lu, Zehui Guo, David Yuanda Gan +4Jailbreak AttacksImage-to-Video Generation

  23. Direct, Parallel, or Sequential? A Comparative Study of Training-Free Multi-Subject Image-to-Video Generation

    Aug 24, 2026Yanliang Qi, Kexi Chen, Muchao Ye +1Image-to-Video GenerationControllable Video Generation

  24. HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

    Aug 13, 2026Jiazi Bu, Pengyang Ling, Yujie Zhou +10Image-to-Video GenerationVideo Diffusion Models

  25. Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

    Aug 12, 2026Aman Tyagi, Hemanth Boinpally, Jonathan Chen +2Image-to-Video GenerationAgentic Video Generation