Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape problem. Although diffusion models show impressive generative ability, their exploration in talking head generation remains unsatisfactory. This is because they either solely use the diffusion model to obtain an intermediate representation and then employ another pre-trained renderer, or they overlook the feature decoupling of complex facial details, such as expressions, head poses and appearance textures. Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages. Specifically, we separate facial details into motion and appearance. In the initial phase, we design the Diffusion Transformer to accurately predict motion coefficients from raw audio. These motions are highly decoupled from appearance, making them easier for the network to learn compared to high-dimensional RGB images. Subsequently, in the second phase, we encode the reference image to capture appearance textures. The predicted facial and head motions and encoded appearance then serve as the conditions for the Diffusion UNet, guiding the frame generation. Benefiting from decoupling facial details and fully leveraging diffusion models, extensive experiments substantiate that our approach excels in enhancing image quality and generating more accurate and diverse results compared to previous state-of-the-art methods.
论文检索
输入标题、作者或关键词，从 1,237 篇学术成果中精准定位
With the rise of new 3D representations like NeRF and 3D Gaussian splatting, creating realistic 3D scenes is easier than ever before. However, the incompatibility of these 3D representations with existing editing software has also introduced unprecedented challenges to 3D editing tasks. Although recent advances in text-to-image generative models have made some progress in 3D editing, these methods either lack precision or require users to manually specify the editing areas in 3D space, complicating the editing process. To overcome these issues, we propose Edit3D, an innovative 3D editing method designed to enhance editing quality. Specifically, we propose a multi-turn editing framework and introduce an attention-driven open-set segmentation (ADSS) technique within this framework. ADSS allows for more precise segmentation of parts, which enhances the editing precision and minimizes interference with pixels in areas that are not being edited. Additionally, we propose a fine-tuning phase, intended to further improve the overall editing quality without compromising the training efficiency. Experiments demonstrate that Edit3D effectively adjusts 3D scenes based on textual instructions. Through continuous and multiple turns of editing, it achieves more intricate combinations, enhancing the diversity of 3D editing effects. Code is available at https://github.com/PeterouZh/Edit3D.
Mitigating Social Biases in Text-to-Image Diffusion Models via Linguistic-Aligned Attention Guidance
Recent advancements in text-to-image generative models have showcased remarkable capabilities across various tasks. However, these powerful models have revealed the inherent risks of social biases. Such biases can propagate distorted real-world perspectives and spread unforeseen prejudice and discrimination. Current debiasing methods are primarily designed for scenarios with a single individual in the image and exhibit homogenous race or gender when multiple individuals are involved, harming the diversity of social groups within the image. To address this problem, we consider the semantic consistency between text prompts and generated images in text-to-image diffusion models to identify how biases are generated. We propose a novel method to locate where the biases are based on different tokens and then mitigate them for each individual. Specifically, we introduce a Linguistic-aligned Attention Guidance module consisting of Block Voting and Linguistic Alignment, to effectively locate the semantic regions related to biases. Additionally, we employ Fair Inference in these regions to generate fair attributes across arbitrary distributions while preserving the original structural and semantic information. Extensive experiments and analyses demonstrate our method outperforms existing methods for debiasing with multiple individuals across various scenarios.
Point clouds from real-world scenarios inevitably contain complex noise, significantly impairing the accuracy of downstream tasks. To tackle this challenge, cascading encoder-decoder architecture has become a conventional technical route to iterative denoise. However, circularly feeding the output of denoiser as its input again involves the re-extraction of underlying surface, leading to unstable denoising process and over-smoothed geometric details. To address these issues, we propose a novel denoising paradigm dubbed PD-Refiner that employs a single encoder to model the underlying surface. Then, we leverage several lightweight hierarchical Underlying Surface Inheritance Refiners (USIRs) to inherit and strengthen it, thereby avoiding the re-extraction from the intermediate point cloud. Furthermore, we design adaptive edge-aware supervision to improve the edge awareness of the USIRs, allowing for the adjustment of the denoising preferences from global structure to local details. The results demonstrate that our method not only achieves state-of-the-art performance in terms of denoising stability and efficacy, but also enhances edge clarity and point cloud uniformity.
Pixel-level fine-grained image editing remains an open challenge. Previous works fail to achieve an ideal trade-off between control granularity and inference speed. They either fail to achieve pixel-level fine-grained control, or their inference speed requires optimization. To address this, this paper for the first time employs a regression-based network to learn the variation patterns of StyleGAN latent codes during the image dragging process. This method enables pixel-level precision in dragging editing with little time cost. Users can specify handle points and their corresponding target points on any GAN-generated images, and our method will move each handle point to its corresponding target point. Through experimental analysis, we discover that a short movement distance from handle points to target points yields a high-fidelity edited image, as the model only needs to predict the movement of a small portion of pixels. To achieve this, we decompose the entire movement process into multiple sub-processes. Specifically, we develop a transformer encoder-decoder based network named 'Latent Predictor' to predict the latent code motion trajectories from handle points to target points in an autoregressive manner. Moreover, to enhance the prediction stability, we introduce a component named 'Latent Regularizer', aimed at constraining the latent code motion within the distribution of natural images. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) inference speed and image editing performance at the pixel-level granularity.
Recent advancements in 3D generation have garnered considerable interest due to their potential applications. Despite these advancements, the field faces persistent challenges in multi-conditional control, primarily due to the lack of paired datasets and the inherent complexity of 3D structures. To address these challenges, we introduce ImageBind3D, a novel framework for controllable 3D generation that integrates text, hand-drawn sketches, and depth maps to enhance user controllability. Our innovative contribution is adopting an inversion-align strategy, facilitating controllable 3D generation without requiring paired datasets. Firstly, utilizing GET3D as a baseline, our method innovates a 3D inversion technique that synchronizes 2D images with 3D shapes within the latent space of 3D GAN. Subsequently, we leverage images as intermediaries to facilitate pseudo-pairing between the shapes and various modalities. Moreover, our multi-modal diffusion model design strategically aligns external control signals with the generative model's latent knowledge, enabling precise and controllable 3D generation. Extensive experiments validate that ImageBind3D surpasses existing state-of-the-art methods in both fidelity and controllability. Additionally, our approach can offer composable guidance for any feed-forward 3D generative models, significantly enhancing their controllability.
Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines. While advances have been made in natural language processing, real-world humor often thrives in a multi-modal context, encapsulated distinctively by memes. This paper poses a particular emphasis on the impact of multi-images on meme captioning. After that, we introduce the XMeCap framework, a novel approach that adopts supervised fine-tuning and reinforcement learning based on an innovative reward model, which factors in both global and local similarities between visuals and text. Our results, benchmarked against contemporary models, manifest a marked improvement in caption generation for both single-image and multi-image memes, as well as different meme categories. XMeCap achieves an average evaluation score of 75.85 for single-image memes and 66.32 for multi-image memes, outperforming the best baseline by 3.71% and 4.82%, respectively. This research not only establishes a new frontier in meme-related studies but also underscores the potential of machines in understanding and generating humor in a multi-modal setting.
Recent developments in diffusion models have demonstrated an exceptional capacity to generate high-quality, prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image editing, which tend to be less effective when making precise edits to specific objects or fine-grained regions within a scene containing single/multiple objects. We introduce a novel framework for zero-shot localized multi-object editing through a multi-diffusion process to overcome this challenge. This framework empowers users to perform various operations on objects within an image, such as adding, replacing, or editing many objects in a complex scene in one pass. Our approach leverages foreground masks and corresponding simple text prompts that exert localized influences on the target regions resulting in high-fidelity image editing. A combination of cross-attention and background preservation losses within the latent space ensures that the characteristics of the object being edited are preserved while simultaneously achieving a high-quality, seamless reconstruction of the background with fewer artifacts compared to the state-of-the-art (SOTA). We also curate and release a dataset dedicated to multi-object editing, named LoMOE-Bench. Our experiments against existing SOTA demonstrate the improved effectiveness of our approach in terms of both image editing quality, and inference speed.
In this paper, we introduce a new challenging task called Zero-Shot Controllable Image-to-Video Animation, where the goal is to animate an image based on motion trajectories defined by the user, without fine-tuning the base model. Primary challenges include maintaining consistency of background, consistency of object in motion, faithfulness to the user-defined trajectory, and quality of motion animation. We also introduce a novel approach for this task, leveraging diffusion models called Img2VidAnim-Zero (IVA0). IVA0 tackles our controllable Image-to-Video (I2V) task by decomposing it into two subtasks: 'out-of-place' and 'in-place' motion animation. Due to this decomposition, IVA0 can leverage existing work on layout-conditioned image generation for out-of-place motion generation, and existing text-conditioned video generation methods for in-place motion animation, thus facilitating zero-shot generation. Our model also addresses key challenges for controllable animation, such as Layout Conditioning via Spatio-Temporal Masking to incorporate user guidance and Motion Afterimage Suppression (MAS) scheme to reduce object ghosting during out-of-place animation. Finally, we design a novel controllable I2V benchmark featuring diverse local- and global-level metrics. Results show IVA0 as a new state-of-the-art, establishing a new standard for the zero-shot controllable I2V task. Our method highlights the simplicity and effectiveness of task decomposition and modularization for this novel task for future studies. Our code and visualizations are available at https://img2vidanim-0.github.io/
Generating photorealistic animations from a single still photo represents a significant advancement in multimedia editing and artistic creation. While existing AIGC methods have reached milestone successes, they often struggle with maintaining consistency with real-world physical laws, particularly in fluid dynamics. To address this issue, this paper introduces ANFluid, a physics solver and data-driven coupled framework that combines physics-aware simulation (PAS) and dual-flow texture learning (DFTL) to animate natural fluid photos effectively. The PAS component of ANFluid ensures that motion guides adhere to physical laws, and can be automatically tailored with specific numerical solver to meet the diversities of different fluid scenes. Concurrently, DFTL focuses on enhancing texture prediction. It employs bidirectional self-supervised optical flow estimation and multi-scale wrapping to strengthen dynamic relationships and elevate the overall animation quality. Notably, despite being built on a transformer architecture, the innovative encoder-decoder design in DFTL does not increase the parameter count but rather enhances inference efficiency. Extensive quantitative experiments have shown that our ANFluid surpasses most current methods on the Holynski and CLAW datasets. User studies further confirm that animations produced by ANFluid maintain better physical and content consistency with the real world and the original input, respectively. Moreover, ANFluid supports interactive editing during the simulation process, enriching the animation content and broadening its application potential.
Exemplar-based image translation has garnered significant interest from researchers due to its broad applications in multimedia/multimodal processing. Existing methods primarily employ Euclidean-based losses to implicitly establish cross-domain correspondences between exemplar and conditional images, aiming to produce high-fidelity images. However, these methods often suffer from two challenges: 1) Insufficient excavation of domain-invariant features leads to low-quality cross-domain correspondences, and 2) Inaccurate correspondences result in errors propagated during the translation process due to a lack of reliable prior guidance. To tackle these issues, we propose a novel prior-guided diffusion model with global-local contrastive learning (PROMOTE), which is trained in a self-supervised manner. Technically, global-local contrastive learning is designed to align two cross-domain images within hyperbolic space and reduce the gap between their semantic correlation distributions using the Fisher-Rao metric, allowing the visual encoders to extract domain-invariant features more effectively. Moreover, a prior-guided diffusion model is developed that propagates the structural prior to all timesteps in the diffusion process. It is optimized by a novel prior denoising loss, mathematically derived from the transitions modified by prior information in a self-supervised manner, successfully alleviating the impact of inaccurate correspondences on image translation. Extensive experiments conducted across seven datasets demonstrate that our proposed PROMOTE significantly exceeds state-of-the-art performance in diverse exemplar-based image translation tasks. The source code is publicly available at http://github.com/zgj77/PROMOTE.
Social media has become ubiquitous for connecting with others, staying updated with news, expressing opinions, and finding entertainment. However, understanding the intention behind social media posts remains challenging due to the implicit and commonsense nature of these intentions, the need for cross-modality understanding of both text and images, and the presence of noisy information such as hashtags, misspelled words, and complicated abbreviations. To address these challenges, we present MIKO, a Multimodal Intention Knowledge DistillatiOn framework that collaboratively leverages a Large Language Model (LLM) and a Multimodal Large Language Model (MLLM) to uncover users' intentions. Specifically, our approach uses an MLLM to interpret the image, an LLM to extract key information from the text, and another LLM to generate intentions. By applying MIKO to publicly available social media datasets, we construct an intention knowledge base featuring 1,372K intentions rooted in 137,287 posts. Moreover, We conduct a two-stage annotation to verify the quality of the generated knowledge and benchmark the performance of widely used LLMs for intention generation, and further apply MIKO to a sarcasm detection dataset and distill a student model to demonstrate the downstream benefits of applying intention knowledge.
Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this challenge. Yet, this defensive measure unintentionally fuels the continued refinement of generative models. Watermarking emerges as a proactive and sustainable tactic, preemptively regulating the creation and dissemination of synthesized content. Thus, this paper, as a pioneer, proposes the generative robust audiowatermarking method (Groot), presenting a paradigm for proactively supervising the synthesized audio and its source diffusion models. In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously, facilitated by parameter-fixed diffusion models equipped with a dedicated encoder. The watermark embedded within the audio can subsequently be retrieved by a lightweight decoder. The experimental results highlight Groot's outstanding performance, particularly in terms of robustness, surpassing that of the leading state-of-the-art methods. Beyond its impressive resilience against individual post-processing attacks, Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%. Our audio samples are available at https://groot-gaw.github.io/.
Object detectors often suffer a decrease in performance due to the large domain gap between the training data (source domain) and real-world data (target domain). Diffusion-based generative models have shown remarkable abilities in generating high-quality and diverse images, suggesting their potential for extracting valuable feature from various domains. To effectively leverage the cross-domain feature representation of diffusion models, in this paper, we train a detector with frozen-weight diffusion model on the source domain, then employ it as a teacher model to generate pseudo labels on the unlabeled target domain, which are used to guide the supervised learning of the student model on the target domain. We refer to this approach as Diffusion Domain Teacher (DDT). By employing this straightforward yet potent framework, we significantly improve cross-domain object detection performance without compromising the inference speed. Our method achieves an average mAP improvement of 21.2% compared to the baseline on 6 datasets from three common cross-domain detection benchmarks (Cross-Camera, Syn2Real, Real2Artistic), surpassing the current state-of-the-art (SOTA) methods by an average of 5.7% mAP. Furthermore, extensive experiments demonstrate that our method consistently brings improvements even in more powerful and complex models, highlighting broadly applicable and effective domain adaptation capability of our DDT.
DAFT-GAN: Dual Affine Transformation Generative Adversarial Network for Text-Guided Image Inpainting
In recent years, there has been a significant focus on research related to text-guided image inpainting. However, the task remains challenging due to several constraints, such as ensuring alignment between the image and the text, and maintaining consistency in distribution between corrupted and uncorrupted regions. In this paper, thus, we propose a dual affine transformation generative adversarial network (DAFT-GAN) to maintain the semantic consistency for text-guided inpainting. DAFT-GAN integrates two affine transformation networks to combine text and image features gradually for each decoding block. Moreover, we minimize information leakage of uncorrupted features for fine-grained image generation by encoding corrupted and uncorrupted regions of the masked image separately. Our proposed model outperforms the existing GAN-based models in both qualitative and quantitative assessments with three benchmark datasets (MS-COCO, CUB, and Oxford) for text-guided image inpainting.
Recent advancements in the field of Diffusion Transformers have substantially improved the generation of high-quality 2D images, 3D videos, and 3D shapes. However, the effectiveness of the Transformer architecture in the domain of co-speech gesture generation remains relatively unexplored, as prior methodologies have predominantly employed the Convolutional Neural Network (CNNs) or simple a few transformer layers. In an attempt to bridge this research gap, we introduce a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G, which directly implements the denoising process on gesture sequences. To enhance the contextual reasoning capability of temporally aligned speech-driven gestures, we incorporate a novel Masked Diffusion Transformer. This model employs a mask modeling scheme specifically designed to strengthen temporal relation learning among sequence gestures, thereby expediting the learning process and leading to coherent and realistic motions. Apart from audio, Our MDT-A2G model also integrates multi-modal information, encompassing text, emotion, and identity. Furthermore, we propose an efficient inference strategy that diminishes the denoising computation by leveraging previously calculated results, thereby achieving a speedup with negligible performance degradation. Experimental results demonstrate that MDT-A2G excels in gesture generation, boasting a learning speed that is over 6× faster than traditional diffusion transformers and an inference speed that is 5.7× than the standard diffusion model. Our code is available at https://xiaofenmao.github.io/web-project/MDT-A2G/
The field of floorplan generation has attracted significant interest from the community. Remarkably, recent advances in generative models have markedly enhanced the development of this field. However, generating floorplans that satisfy various conditions remains a challenging task. This paper proposes a learning framework, named Cons2Plan, for automatically and high-quality generating vector floorplans from various conditions. The input conditions can be graphs, boundaries, or a combination of both. The conditional diffusion model is the core component of our Cons2Plan. The denoising network uses a conditional embedding module to incorporate the conditions during the reverse process. Additionally, Cons2Plan incorporates a two-stage approach that generates graph conditions based on boundaries. It uses three networks for node prediction and a novel conditional edge generation diffusion model, named CEDM, for edge generation. We conduct qualitative evaluations, quantitative comparisons, and ablation studies to show that our method produces better floorplans than state-of-the-art methods.
DIG: Complex Layout Document Image Generation with Authentic-looking Text for Enhancing Layout Analysis
PDF ↗Even though significant progress has been made in standardizing document layout analysis, complex layout documents like magazines and newspapers still present challenges. Models trained on standardized documents struggle with these complexities, and the high cost of annotating such documents limits dataset availability. To address this, we propose the Complex Layout Document Image Generation (DIG) model, which can generate diverse document images with complex layouts and authentic-looking text, aiding in layout analysis model training. Concretely, we first pre-train DIG on a large-scale document dataset with a text-sensitive loss function to address the issue of unreal generation of text regions. Then, we fine-tune it with a small number of documents with complex layouts to generate new images with the same layout. Additionally, we use a layout generation model to create new layouts, enhancing data diversity. Finally, we design a box-wise quality scoring function to filter out low-quality regions during layout analysis model training to enhance the effectiveness of using the generated images. Experimental results on the DSSE-200 and PRImA datasets show when incorporating generated images from DIG, the mAP of the layout analysis model is improved from 47.05 to 56.07 and from 53.80 to 62.26, respectively, which is a 19.17% and 15.72% enhancement compared to the baseline.
Singing Voice Synthesis (SVS) has significantly advanced with deep generative models, achieving high audio quality but still struggling with musicality, mainly due to the lack of performance control over timing, dynamics, and pitch, which are essential for music expression. Additionally, integrating data and supporting diverse languages and styles in SVS remain challenging. To tackle these issues, this paper presents ExpressiveSinger, an SVS framework that leverages a cascade of diffusion models to generate realistic singing across multiple languages, styles, and techniques from scores and lyrics. Our approach begins with consolidating, cleaning, annotating, and processing public singing datasets, developing a multilingual phoneme set, and incorporating different musical styles and techniques. We then design methods for generating expressive performance control signals including phoneme timing, F0 curves, and amplitude envelopes, which enhance musicality and model consistency, introduce more controllability, and reduce data requirements. Finally, we generate mel-spectrograms and audio from performance control signals with style guidance and singer timbre embedding. Our models also enable trained singers to sing in new languages and styles. Several listening tests reveal both musicality and controllability of our generated singing compared with existing works and human singing. We release the data for future research. Demo: https://shuqid.net/expressive-singing-synthesis.