4d_2025.md

%accepted papers

@inproceedings{jinoptimizing,
  title={Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images},
  author={Jin, In-Hwan and Choo, Haesoo and Jeong, Seong-Hun and Heemoon, Park and Kim, Junghwan and Kwon, Oh-joon and Kong, Kyeongbo},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}

@article{bian2025gsdit,
  title={GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking},
  author={Bian, Weikang and Huang, Zhaoyang and Shi, Xiaoyu and and Li, Yijin and Wang, Fu-Yun and Li, Hongsheng},
  journal={arXiv preprint arXiv:2501.02690},
  year={2025}
}

@article{jin2024stereo4d,
  title={Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos}, 
  author={Jin, Linyi and Tucker, Richard and Li, Zhengqi and Fouhey, David and Snavely, Noah and Holynski, Aleksander},
  journal={CVPR},
  year={2025},
}

@article{yao2025uni4d,
  title={Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video},
  author={Yao, David Yifan and Zhai, Albert J and Wang, Shenlong},
  journal={arXiv preprint arXiv:2503.21761},
  year={2025}
}

@inproceedings{wu20254d,
  title={4D-Fly: Fast 4D Reconstruction from a Single Monocular Video},
  author={Wu, Diankun and Liu, Fangfu and Hung, Yi-Hsin and Qian, Yue and Zhan, Xiaohang and Duan, Yueqi},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={16663--16673},
  year={2025}
}

@inproceedings{chu2025robust,
  title={Robust Multi-Object 4D Generation for In-the-wild Videos},
  author={Chu, Wen-Hsuan and Ke, Lei and Liu, Jianmeng and Huo, Mingxiao and Tokmakov, Pavel and Fragkiadaki, Katerina},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={22067--22077},
  year={2025}
}

@inproceedings{li2025articulated,
  title={Articulated Kinematics Distillation from Video Diffusion Models},
  author={Li, Xuan and Ma, Qianli and Lin, Tsung-Yi and Chen, Yongxin and Jiang, Chenfanfu and Liu, Ming-Yu and Xiang, Donglai},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={17571--17581},
  year={2025}
}

@article{liu2025free4d,
     title={Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency},
     author={Liu, Tianqi and Huang, Zihao and Chen, Zhaoxi and Wang, Guangcong and Hu, Shoukang and Shen, liao and Sun, Huiqiang and Cao, Zhiguo and Li, Wei and Liu, Ziwei},
     journal={arXiv preprint arXiv:2503.20785},
     year={2025}
}

@inproceedings{st4rtrack2025,
  title={St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World},
  author={Feng*, Haiwen and Zhang*, Junyi and Wang, Qianqian and Ye, Yufei and Yu, Pengcheng and Black, Michael J. and Darrell, Trevor and Kanazawa, Angjoo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2025}
}

@inproceedings{zhou2025vlm4d,
    title={VLM4D: Towards Spatiotemporal Awareness in Vision Language Models},
    author={Zhou, Shijie and Vilesov, Alexander and He, Xuehai and Wan, Ziyu and Zhang, Shuwang and Nagachandra, Aditya and Chang, Di and Chen, Dongdong and Wang, Eric Xin and Kadambi, Achuta},
    booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
    year={2025}
}

@misc{aloni2025express4dexpressivefriendlyextensible,
title={Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark}, 
author={Yaron Aloni and Rotem Shalev-Arkushin and Yonatan Shafir and Guy Tevet and Ohad Fried and Amit Haim Bermano},
year={2025},
eprint={2508.12438},
archivePrefix={arXiv},
primaryClass={cs.GR},
url={https://arxiv.org/abs/2508.12438}
}

@article{xie2025citydreamer4d,
  title={CityDreamer4D: Compositional generative model of unbounded 4D cities},
  author={Xie, Haozhe and Chen, Zhaoxi and Hong, Fangzhou and Liu, Ziwei},
  journal={arXiv e-prints},
  pages={arXiv--2501},
  year={2025}
}

@article{zhen2025tesseract,
  title={TesserAct: learning 4D embodied world models},
  author={Zhen, Haoyu and Sun, Qiao and Zhang, Hongxin and Li, Junyan and Zhou, Siyuan and Du, Yilun and Gan, Chuang},
  journal={arXiv preprint arXiv:2504.20995},
  year={2025}
}

@misc{luo2025t2bstexttocharacterblendshapesvideo,
      title={T2Bs: Text-to-Character Blendshapes via Video Generation}, 
      author={Jiahao Luo and Chaoyang Wang and Michael Vasilkovsky and Vladislav Shakhrai and Di Liu and Peiye Zhuang and Sergey Tulyakov and Peter Wonka and Hsin-Ying Lee and James Davis and Jian Wang},
      year={2025},
      eprint={2509.10678},
      archivePrefix={arXiv},
      primaryClass={cs.GR},
      url={https://arxiv.org/abs/2509.10678}, 
}

@article{jiang2025geo4d,
  title={Geo4d: Leveraging video generators for geometric 4d scene reconstruction},
  author={Jiang, Zeren and Zheng, Chuanxia and Laina, Iro and Larlus, Diane and Vedaldi, Andrea},
  journal={arXiv preprint arXiv:2504.07961},
  year={2025}
}

@article{yao2025sv4d,
  title={Sv4d 2.0: Enhancing spatio-temporal consistency in multi-view video diffusion for high-quality 4d generation},
  author={Yao, Chun-Han and Xie, Yiming and Voleti, Vikram and Jiang, Huaizu and Jampani, Varun},
  journal={arXiv preprint arXiv:2503.16396},
  year={2025}
}

@article{zhou2025holotime,
  title={HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation},
  author={Zhou, Haiyang and Yu, Wangbo and Guan, Jiawen and Cheng, Xinhua and Tian, Yonghong and Yuan, Li},
  journal={arXiv preprint arXiv:2504.21650},
  year={2025}
}

@article{zhang2025stable,
  title={Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation},
  author={Zhang, Hao and Yao, Chun-Han and Donn{\'e}, Simon and Ahuja, Narendra and Jampani, Varun},
  journal={arXiv preprint arXiv:2509.10687},
  year={2025}
}

@article{nag20252,
  title={In-2-4d: Inbetweening from two single-view images to 4d generation},
  author={Nag, Sauradip and Cohen-Or, Daniel and Zhang, Hao and Mahdavi-Amiri, Ali},
  journal={arXiv preprint arXiv:2504.08366},
  year={2025}
}

@inproceedings{sun2025animus3d,
  title={Animus3D: Text-driven 3D Animation via Motion Score Distillation},
  author={Sun, Qi and Wang, Can and Shang, Jiaxiang and Feng, Wensen and Liao, Jing},
  booktitle={Proceedings of the SIGGRAPH Asia 2025 Conference Papers},
  pages={1--11},
  year={2025}
}

@inproceedings{zheng2025trackinpaintresplat,
  title={Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling},
  author={Zheng, Shuhong and Mirzaei, Ashkan and Gilitschenski, Igor},
  booktitle={NeurIPS},
  year={2025}
}

@article{wang20254real,
  title={4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation},
  author={Wang, Chaoyang and Mirzaei, Ashkan and Goel, Vidit and Menapace, Willi and Siarohin, Aliaksandr and Vinella, Avalon and Vasilkovsky, Michael and Skorokhodov, Ivan and Shakhrai, Vladislav and Korolev, Sergey and others},
  journal={arXiv preprint arXiv:2506.18839},
  year={2025}
}

@article{ma20254d,
  title={4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time},
  author={Ma, Ziqiao and Chen, Xuweiyi and Yu, Shoubin and Bi, Sai and Zhang, Kai and Ziwen, Chen and Xu, Sihan and Yang, Jianing and Xu, Zexiang and Sunkavalli, Kalyan and others},
  journal={arXiv preprint arXiv:2506.18890},
  year={2025}
}

@inproceedings{sang2025twosquared,
  title={Twosquared: 4d generation from 2d image pairs},
  author={Sang, Lu and Canfes, Zehranaz and Marin, Riccardo and Cao, Dongliang and Bernard, Florian and Cremers, Daniel},
  booktitle={Thirteenth International Conference on 3D Vision},
  year={2025}
}

@article{zhou2025omniworld,
  title={Omniworld: A multi-domain and multi-modal dataset for 4d world modeling},
  author={Zhou, Yang and Wang, Yifan and Zhou, Jianjun and Chang, Wenzheng and Guo, Haoyu and Li, Zizun and Ma, Kaijing and Li, Xinyue and Wang, Yating and Zhu, Haoyi and others},
  journal={arXiv preprint arXiv:2509.12201},
  year={2025}
}

@article{bahmani2025lyra,
  title={Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation},
  author={Bahmani, Sherwin and Shen, Tianchang and Ren, Jiawei and Huang, Jiahui and Jiang, Yifeng and Turki, Haithem and Tagliasacchi, Andrea and Lindell, David B and Gojcic, Zan and Fidler, Sanja and others},
  journal={arXiv preprint arXiv:2509.19296},
  year={2025}
}

@article{yenphraphai2025shapegen4d,
  title={Shapegen4d: Towards high quality 4d shape generation from videos},
  author={Yenphraphai, Jiraphon and Mirzaei, Ashkan and Chen, Jianqi and Zou, Jiaxu and Tulyakov, Sergey and Yeh, Raymond A and Wonka, Peter and Wang, Chaoyang},
  journal={arXiv preprint arXiv:2510.06208},
  year={2025}
}

@article{mi2025one4d,
  title={One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control},
  author={Mi, Zhenxing and Wang, Yuxin and Xu, Dan},
  journal={arXiv preprint arXiv:2511.18922},
  year={2025}
}

@inproceedings{zhu2026ar4d,
  title={Ar4d: Autoregressive 4d generation from monocular videos},
  author={Zhu, Hanxin and He, Tianyu and Chen, Zhibo},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={88--98},
  year={2026}
}

@inproceedings{lin2026movies,
  title={Movies: Motion-aware 4d dynamic view synthesis in one second},
  author={Lin, Chenguo and Lin, Yuchen and Pan, Panwang and Yu, Yifan and Hu, Tao and Yan, Honglei and Fragkiadaki, Katerina and Mu, Yadong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={295--306},
  year={2026}
}

@inproceedings{gui2026object,
  title={Object-Aware 4D Human Motion Generation},
  author={Gui, Shurui and Patel, Deep and Li, Xiner and Min, Martin Renqiang},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11563--11572},
  year={2026}
}

@inproceedings{yuan2026seeu,
  title={SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation},
  author={Yuan, Yu and Wickremasinghe, Tharindu and Nadir, Zeeshan and Wang, Xijun and Chi, Yiheng and Chan, Stanley H},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11150--11162},
  year={2026}
}

@inproceedings{xie2026sonic4d,
  title={Sonic4d: Spatial audio generation for immersive 4d scene exploration},
  author={Xie, Siyi and Zhu, Hanxin and Chen, Xinyi and He, Tianyu and Li, Xin and Chen, Zhibo},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={40},
  number={13},
  pages={11087--11095},
  year={2026}
}

@inproceedings{lu2026see4d,
  title={See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting},
  author={Lu, Dongyue and Liang, Ao and Huang, Tianxin and Fu, Xiao and Zhao, Yuyang and Ma, Baorui and Pan, Liang and Yin, Wei and Kong, Lingdong and Ooi, Wei Tsang and others},
  booktitle={Computer Graphics Forum},
  pages={e70345},
  year={2026},
  organization={Wiley Online Library}
}

@article{zhang2025joint,
  title={Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image},
  author={Zhang, Yanran and Wang, Ziyi and Zheng, Wenzhao and Zhu, Zheng and Zhou, Jie and Lu, Jiwen},
  journal={arXiv preprint arXiv:2512.05044},
  year={2025}
}

%axiv papers

@article{yang2025widerange4d,
  title={WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes},
  author={Yang, Ling and Zhu, Kaixin and Tian, Juanxi and Zeng, Bohan and Lin, Mingbao and Pei, Hongjuan and Zhang, Wentao and Yan, Shuichen},
  journal={arXiv preprint arXiv:2503.13435},
  year={2025}
}

@misc{chen2025deepverse4dautoregressivevideo,
      title={DeepVerse: 4D Autoregressive Video Generation as a World Model}, 
      author={Junyi Chen and Haoyi Zhu and Xianglong He and Yifan Wang and Jianjun Zhou and Wenzheng Chang and Yang Zhou and Zizun Li and Zhoujie Fu and Jiangmiao Pang and Tong He},
      year={2025},
      eprint={2506.01103},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.01103}, 
}

@misc{rozumnyi2025bulletgenimproving4dreconstruction,
      title={BulletGen: Improving 4D Reconstruction with Bullet-Time Generation}, 
      author={Denys Rozumnyi and Jonathon Luiten and Numair Khan and Johannes Schönberger and Peter Kontschieder},
      year={2025},
      eprint={2506.18601},
      archivePrefix={arXiv},
      primaryClass={cs.GR},
      url={https://arxiv.org/abs/2506.18601}, 
}

@article{chen20254dnex,
    title={4DNeX: Feed-Forward 4D Generative Modeling Made Easy},
    author={Chen, Zhaoxi and Liu, Tianqi and Zhuo, Long and Ren, Jiawei and Tao, Zeng and Zhu, He and Hong, Fangzhou and Pan, Liang and Liu, Ziwei},
    journal={arXiv preprint arXiv:2508.13154},
    year={2025}
}

@article{pan2025diff4splat,
  title={Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models},
  author={Pan, Panwang and Lin, Chenguo and Zhao, Jingjing and Li, Chenxin and Lin, Yuchen and Li, Haopeng and Yan, Honglei and Wen, Kairun and Lin, Yunlong and Yuan, Yixuan and others},
  journal={arXiv preprint arXiv:2511.00503},
  year={2025}
}

@article{gong2025swit4d,
  title     = {SWiT-4D: Sliding-Window Transformer for Lossless and Parameter-Free Temporal 4D Generation},
  author    = {Gong, Kehong and Wen, Zhengyu and Xu, Mingxi and He, Weixia and Wang, Qi and 
               Zhang, Ning and Li, Zhengyu and Li, Chenbin and Lian, Dongze and
               Zhao, Wei and He, Xiaoyu and Zhang, Mingyuan},
  journal   = {arXiv preprint arXiv:2512.10860},
  year      = {2025}
}