2nd AI for Content Generation, Quality Enhancement and Streaming
Multi-Scale Contrastive-Adversarial Distillation for Super-Resolution-
[pdf]
[bibtex]@InProceedings{Ko_2025_ICCV, author = {Ko, Donggeun and Kwak, Youngsang and Kim, San and Kwak, Jaehwa and Kim, Jaekwang}, title = {Multi-Scale Contrastive-Adversarial Distillation for Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {5069-5078} }
C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales-
[pdf]
[bibtex]@InProceedings{Jiang_2025_ICCV, author = {Jiang, Yuxuan and Zeng, Chengxi and Teng, Siyue and Zhang, Fan and Zhu, Xiaoqing and Sole, Joel and Bull, David}, title = {C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {5058-5068} }
High-Fidelity 4x Neural Reconstruction of Real-time Path Traced Videos-
[pdf]
[bibtex]@InProceedings{Lao_2025_ICCV, author = {Lao, Zhiqiang and Chen, Zekai and Cui, Jiali and Conde, Marcos and Timofte, Radu and Yu, Heather}, title = {High-Fidelity 4x Neural Reconstruction of Real-time Path Traced Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {5079-5087} }
VidMP3: Video Editing by Representing Motion with Pose and Position Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mishra_2025_ICCV, author = {Mishra, Sandeep and Saha, Oindrila and Bovik, Alan}, title = {VidMP3: Video Editing by Representing Motion with Pose and Position Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {5037-5047} }
LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2025_ICCV, author = {Tang, Jyun-Ze and Hsu, Chih-Fan and Li, Jeng-Lin and Chang, Ming-Ching and Chen, Wei-Chao}, title = {LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {5048-5057} }