科研成果 by Type: Conference Paper

In this paper, we introduce L-DiffER, a language-based diffusion model designed for the ill-posed single image reflection removal task. Although having shown impressive performance for image generation, existing language-based diffusion models struggle with precise control and faithfulness in image restoration. To overcome these limitations, we propose an iterative condition refinement strategy to resolve the problem of inaccurate control conditions. A multi-condition constraint mechanism is employed to ensure the recovery faithfulness of image color and structure while retaining the generation capability to handle low-transmitted reflections. We demonstrate the superiority of the proposed method through extensive experiments, showcasing both quantitative and qualitative improvements over existing methods.

This paper discusses the so-called Bakers’ Strike Edict from Ephesus  (Ephesos 231 = IK 12.215 p. 27) in light of recent studies on  the Roman imperial toolkit to build empire-wide communities. Clifford Ando and Myles Lavan argued that Roman emperors in the first two centuries CE were consciously blurring distinctions between Roman and non-Roman populations, so that there could be a shared sense of an empire-wide community among people in the provinces.  This paper argues that, in addition to Lavan’s observations, gubernatorial edicts also show concerns and measures that sought to communicate a sense of the communal at the local level. While the focus of discussion is on the edict responding to a bakers’ strike at Ephesus, several other examples from a corpus of gubernatorial edicts are also used in connection with this example. This paper hopes to contribute to Ando’s and Lavan’s arguments by pointing to a lower register of community building visible in gubernatorial edicts. The governors’ concerns for and efforts to creating communal cohesion and their need to balance parallel and at times competing “common goods” not only adds another nuance to the grander community building project at the imperial level, but demonstrates further complications on how praesidial governors – and in particular proconsuls – can and would react to difficult issues at the local level.

Direction of arrival (DoA) estimation in complex environments is a challenging task. The traditional methods suffer from invalidity under low signal-to-noise ratio (SNR) and reverberation conditions, and the data-driven methods lack of generalization to unseen data types. In this paper we propose a robust DoA estimation approach by combining the two methods above. To focus on spatial information modeling, the proposed method directly uses the compressed covariance matrix of the first-order ambisonics (FOA) signal as input, while only white noise is used during training. To adapt to different characteristics of FOA signals in different frequency bands, our method estimates DoA in different frequency bands by particular models, and the subband results are finally integrated together. Experiments are carried out on both simulated and measured datasets, and the results show the superiority of the proposed method than existing baselines under complex conditions and the scalability for unseen data types.