Recent advancements in Text-to-Image (T2I) generative models have yielded impressive results in generating high-fidelity images based on consistent text prompts. However, there is a growing interest in exploring the potential of these models for more diverse reference-based image manipulation tasks that require spatial understanding and visual context. Previous approaches have achieved this by incorporating additional control modules or fine-tuning the generative models specifically for each task until convergence. In this paper, we propose a different perspective. We conjecture that current large-scale T2I generative models already possess the capability to perform these tasks but are not fully activated within the standard generation process. To unlock these capabilities, we introduce a unified Prompt-Guided In-Context inpainting (PGIC) framework, which leverages large-scale T2I models to re-formulate and solve reference-guided image manipulations. In the PGIC framework, the reference and masked target are stitched together as a new input for the generative models, enabling the filling of masked regions as producing final results. Furthermore, we demonstrate that the self-attention modules in T2I models are well-suited for establishing spatial correlations and efficiently addressing challenging reference-guided manipulations. These large T2I models can be effectively driven by task-specific prompts with minimal training cost or even with frozen backbones. We synthetically evaluate the effectiveness of the proposed PGIC framework across various tasks, including reference-guided image inpainting, faithful inpainting, outpainting, local super-resolution, and novel view synthesis. Our results show that PGIC achieves significantly better performance while requiring less computation compared to other fine-tuning based approaches.
相關內容
Despite the ability of existing large-scale text-to-image (T2I) models to generate high-quality images from detailed textual descriptions, they often lack the ability to precisely edit the generated or real images. In this paper, we propose a novel image editing method, DragonDiffusion, enabling Drag-style manipulation on Diffusion models. Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model. It can transform the editing signals into gradients via feature correspondence loss to modify the intermediate representation of the diffusion model. Based on this guidance strategy, we also build a multi-scale guidance to consider both semantic and geometric alignment. Moreover, a cross-branch self-attention is added to maintain the consistency between the original image and the editing result. Our method, through an efficient design, achieves various editing modes for the generated or real images, such as object moving, object resizing, object appearance replacement, and content dragging. It is worth noting that all editing and content preservation signals come from the image itself, and the model does not require fine-tuning or additional modules. Our source code will be available at //github.com/MC-E/DragonDiffusion.
This paper presents a bibliographic study that analyzes works cited in as well as works that cite NIME papers. We build on existing tools to computationally analyze data retrieved from publicly available databases. We present a variety of metrics, statistics, visualizations and trends aiming to provide quantitative figures on the scholarly impact of NIME, influential authors, related publication venues, associated fields of study, and key works published in other venues.
While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well diffusion-pretrained representations generalize to new domains, a crucial ability for any representation. We find that diffusion-pretraining achieves extraordinary domain generalization results for semantic segmentation, outperforming both supervised and self-supervised backbone networks. Motivated by this, we investigate how to utilize the model's unique ability of taking an input prompt, in order to further enhance its cross-domain performance. We introduce a scene prompt and a prompt randomization strategy to help further disentangle the domain-invariant information when training the segmentation head. Moreover, we propose a simple but highly effective approach for test-time domain adaptation, based on learning a scene prompt on the target domain in an unsupervised manner. Extensive experiments conducted on four synthetic-to-real and clear-to-adverse weather benchmarks demonstrate the effectiveness of our approaches. Without resorting to any complex techniques, such as image translation, augmentation, or rare-class sampling, we set a new state-of-the-art on all benchmarks. Our implementation will be publicly available at \url{//github.com/ETHRuiGong/PTDiffSeg}.
The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at //github.com/vvvb-github/AVSegFormer.
In this work, we propose to learn robot geometry as distance fields (RDF), which extend the signed distance field (SDF) of the robot with joint configurations. Unlike existing methods that learn an implicit representation encoding joint space and Euclidean space together, the proposed RDF approach leverages the kinematic chain of the robot, which reduces the dimensionality and complexity of the problem, resulting in more accurate and reliable SDFs. A simple and flexible approach that exploits basis functions to represent SDFs for individual robot links is presented, providing a smoother representation and improved efficiency compared to neural networks. RDF is naturally continuous and differentiable, enabling its direct integration as cost functions in robot tasks. It also allows us to obtain high-precision robot surface points with any desired spatial resolution, with the capability of whole-body manipulation. We verify the effectiveness of our RDF representation by conducting various experiments in both simulations and with the 7-axis Franka Emika robot. We compare our approach against baseline methods and demonstrate its efficiency in dual-arm settings for tasks involving collision avoidance and whole-body manipulation. Project page: //sites.google.com/view/lrdf/home}{//sites.google.com/view/lrdf/home
This paper introduces MVDiffusion, a simple yet effective multi-view image generation method for scenarios where pixel-to-pixel correspondences are available, such as perspective crops from panorama or multi-view images given geometry (depth maps and poses). Unlike prior models that rely on iterative image warping and inpainting, MVDiffusion concurrently generates all images with a global awareness, encompassing high resolution and rich content, effectively addressing the error accumulation prevalent in preceding models. MVDiffusion specifically incorporates a correspondence-aware attention mechanism, enabling effective cross-view interaction. This mechanism underpins three pivotal modules: 1) a generation module that produces low-resolution images while maintaining global correspondence, 2) an interpolation module that densifies spatial coverage between images, and 3) a super-resolution module that upscales into high-resolution outputs. In terms of panoramic imagery, MVDiffusion can generate high-resolution photorealistic images up to 1024$\times$1024 pixels. For geometry-conditioned multi-view image generation, MVDiffusion demonstrates the first method capable of generating a textured map of a scene mesh. The project page is at //mvdiffusion.github.io.
Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We propose a decoupled text-image fusion mechanism and representation learning modules for both "things" and "stuff".1 Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on over 40 datasets, e.g., ADE20K, COCO, Pascal-VOC Part, RefCOCO/RefCOCOg, ODinW and SeginW, HIPIE achieves the state-of-the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentation and object detection), as well as part-level (e.g., part/subpart segmentation) tasks. Our code is released at //github.com/berkeley-hipie/HIPIE.
We present a hierarchical planning framework for dexterous robotic manipulation (HiDex). This framework exploits in-hand and extrinsic dexterity by actively exploring contacts. It generates rigid-body motions and complex contact sequences. Our framework is based on Monte-Carlo Tree Search (MCTS) and has three levels: 1) planning object motions and environment contact modes; 2) planning robot contacts; 3) path evaluation and control optimization that passes the rewards to the upper levels. This framework offers two main advantages. First, it allows efficient global reasoning over high-dimensional complex space created by contacts. It solves a diverse set of manipulation tasks that require dexterity, both intrinsic (using the fingers) and extrinsic (also using the environment), mostly in seconds. Second, our framework allows the incorporation of expert knowledge and customizable setups in task mechanics and models. It requires minor modifications to accommodate different scenarios and robots. Hence, it could provide a flexible and generalizable solution for various manipulation tasks. As examples, we analyze the results on 7 hand configurations and 15 scenarios. We demonstrate 8 of them on two robot platforms.
For an image with multiple scene texts, different people may be interested in different text information. Current text-aware image captioning models are not able to generate distinctive captions according to various information needs. To explore how to generate personalized text-aware captions, we define a new challenging task, namely Question-controlled Text-aware Image Captioning (Qc-TextCap). With questions as control signals, this task requires models to understand questions, find related scene texts and describe them together with objects fluently in human language. Based on two existing text-aware captioning datasets, we automatically construct two datasets, ControlTextCaps and ControlVizWiz to support the task. We propose a novel Geometry and Question Aware Model (GQAM). GQAM first applies a Geometry-informed Visual Encoder to fuse region-level object features and region-level scene text features with considering spatial relationships. Then, we design a Question-guided Encoder to select the most relevant visual features for each question. Finally, GQAM generates a personalized text-aware caption with a Multimodal Decoder. Our model achieves better captioning performance and question answering ability than carefully designed baselines on both two datasets. With questions as control signals, our model generates more informative and diverse captions than the state-of-the-art text-aware captioning model. Our code and datasets are publicly available at //github.com/HAWLYQ/Qc-TextCap.
The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191