Refinement via Regeneration (RvR) reformulates image refinement in unified multimodal models from an editing-based paradigm to a regeneration-based one. The dataset likely contains images and associated data for training or evaluating this novel framework. It was created by researchers from Tsinghua University and Tencent Hunyuan and was last updated on April 29, 2026.
Use Cases
- Training image refinement models based on the regeneration-based paradigm described.
- Benchmarking the performance of unified multimodal models on image editing tasks.
- Studying the differences between editing-based and regeneration-based refinement approaches.
- Developing new multimodal AI applications that leverage the RvR framework.
Strengths
- Framework developed by researchers from Tsinghua University and Tencent Hunyuan.
- Introduces a novel regeneration-based paradigm for image refinement.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- Jiayi Guo, Linqing Wang, Jiangshan Wang, Yang Yue, Zeyu Liu, Zhiyuan Zhao, Qinglin Lu, Gao Huang, Chunyu Wang.
- Freshness
- Last updated 2026-04-29 02:36:01; freshness should be verified.