| Oct 21, 2025 | We present PICABench, a new benchmark and evaluation protocol for assessing physical realism in image editing — an often overlooked dimension in current generative models. PICABench systematically evaluates the physical consequences across eight sub-dimensions spanning optics, mechanics, and state transitions, with a reliable PICAEval protocol combining VLM-as-a-judge and region-level human annotations. We also build PICA-100K, a dataset for learning physics from videos. Evaluations show that physical realism remains a major challenge. PICABench aims to drive the next wave of physics-aware, causally consistent image editing. [Homepage] [GitHub] [ PICABench Dataset] [ PICA-100K Dataset] [Paper]. |
| Sep 10, 2025 | We are excited to announce Lumina-DiMOO, our latest unified multimodal generation and understanding model built upon an advanced discrete diffusion architecture. This framework demonstrates the strong potential of multimodal diffusion large language models (dLLM) to unify diverse tasks within a single, streamlined architecture, while delivering state-of-the-art performance that surpasses many existing unified models. Learn more and explore resources: [Homepage] [GitHub] [HuggingFace]. |
| Sep 01, 2025 | We introduce ArtiMuse, a multimodal large language model (MLLM) for professional aesthetic understanding, which is trained on ArtiMuse-10K, a meticulously curated, expert-annotated dataset. ArtiMuse-10K systematically defines eight explainable and fine-grained aesthetic attributes (e.g., Composition & Design, Visual Elements & Structure), with a wide coverage of diverse visual domains, including graphic design, 3D design, AIGC-generated images, photography, and painting & calligraphy. [Paper] [Homepage] [GitHub] [Online Demo v1.0] Note: ArtiMuse was officially released at WAIC 2025, in the forum “Evolving with AI: The Iteration and Resilience of Artistic Creativity”. |
| Jun 26, 2025 | Our video restoration method DiffVSR was accepted by ICCV2025. [Paper] [Homepage] |
| Apr 22, 2025 | Our video colorization method TCVC has won the CVMJ 2025 Best Paper Honorable Mention Award. |
| Apr 01, 2025 | We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories, including image restoration, image enhancement, weak-semantic dense prediction, and stylization. [Paper] [Homepage] |
| Jul 18, 2024 | GenLV was accepted by ACM MM2024. GenLV is a successive work of PromptGIP, which further broadens the tasks and improves performance. The paper can be found at here. |
| Jul 01, 2024 | Two papers were accepted by ECCV2024. By analyzing the relationships between image degradations, GRIDS propose a grouped learning method to deal with multiple-degradation restoration. X-Restormer is a new general image restoration backbone network, which possesses good task generality and achieves competitive performance across a variety of restoration tasks. |
| May 02, 2024 | PromptGIP was accepted by ICML2024. PromptGIP is a universal model for general image processing that covers image restoration, image enhancement, image feature extraction tasks, etc. Code is available at here. |
| Aug 27, 2023 | One paper was accepted by TPAMI. SRGA is the first quantitative indicator for measuring the generalization ability of blind super-resolution deep models. |
| Mar 25, 2023 | Two papers were accepted by CVPR2023. DegAE is a new pretraining paradigm for low-level vision. MaskedDenoising adopts masked training to enhance the generalization performance of denoising networks. |
| Mar 12, 2023 | Our video colorization method TCVC was accepted by CVMJ. Code is available at here. |
| Aug 25, 2022 | Our survey on Blind Image Super-Resolution has been accepted by TPAMI. Paper Link |
| May 30, 2022 | The extention version of the lightweight photo retouching network CSRNet has been accepted by TMM. Paper links: conference version, journal version. |
| Aug 31, 2020 | We have won the 3rd place of UDC2020 Challenge on Image Restoration of Under-Display Camera (in conjunction with ECCV2020). The technique report of the proposed RDUnet model can be found at here. The official challenge report can be found at here. |
| Aug 26, 2020 | We have won the 1st place of AIM2020 Video Temporal Super-Resolution Challenge (in conjunction with ECCV2020). The technique report of the proposed EQVI model can be found at here. Code is available at here. The official challenge report can be found at here. |
| Jul 18, 2020 | Our proposed lightweight photo retouching method CSRNet was accepted by ECCV2020. |