Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}
Gait recognition is one of the most important long-distance identification technologies and increasingly gains popularity in both research and industry communities. Although significant progress has been made in indoor datasets, much evidence shows that gait recognition techniques perform poorly in the wild. More importantly, we also find that many conclusions from prior works change with the evaluation datasets. Therefore, the more critical goal of this paper is to present a comprehensive benchmark study for better practicality rather than only a particular model for better performance. To this end, we first develop a flexible and efficient gait recognition codebase named OpenGait. Based on OpenGait, we deeply revisit the recent development of gait recognition by re-conducting the ablative experiments. Encouragingly, we find many hidden troubles of prior works and new insights for future research. Inspired by these discoveries, we develop a structurally simple, empirically powerful and practically robust baseline model, GaitBase. Experimentally, we comprehensively compare GaitBase with many current gait recognition methods on multiple public datasets, and the results reflect that GaitBase achieves significantly strong performance in most cases regardless of indoor or outdoor situations. The source code is available at \url{https://github.com/ShiqiYu/OpenGait}.
Gait is one of the most promising biometrics to identify individuals at a long distance. Although most previous methods have focused on recognizing the silhouettes, several end-to-end methods that extract gait features directly from RGB images perform better. However, we argue that these end-to-end methods inevitably suffer from the gait-unrelated noises, i.e., low-level texture and colorful information. Experimentally, we design both the cross-domain evaluation and visualization to stand for this view. In this work, we propose a novel end-to-end framework named GaitEdge which can effectively block gait-unrelated information and release end-to-end training potential. Specifically, GaitEdge synthesizes the output of the pedestrian segmentation network and then feeds it to the subsequent recognition network, where the synthetic silhouettes consist of trainable edges of bodies and fixed interiors to limit the information that the recognition network receives. Besides, GaitAlign for aligning silhouettes is embedded into the GaitEdge without loss of differentiability. Experimental results on CASIA-B and our newly built TTG-200 indicate that GaitEdge significantly outperforms the previous methods and provides a more practical end-to-end paradigm for blocking RGB noises effectively. All the source code will be released.