Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion.
Artifact-free super-resolution (SR) aims to translate low-resolution images into their high-resolution counterparts with a strict integrity of the original content, eliminating any distortions or synthetic details. While traditional diffusion-based SR techniques have demonstrated remarkable abilities to enhance image detail, they are prone to artifact introduction during iterative procedures. Such artifacts, ranging from trivial noise to unauthentic textures, deviate from the true structure of the source image, thus challenging the integrity of the super-resolution process. In this work, we propose Self-Adaptive Reality-Guided Diffusion (SARGD), a training-free method that delves into the latent space to effectively identify and mitigate the propagation of artifacts. Our SARGD begins by using an artifact detector to identify implausible pixels, creating a binary mask that highlights artifacts. Following this, the Reality Guidance Refinement (RGR) process refines artifacts by integrating this mask with realistic latent representations, improving alignment with the original image. Nonetheless, initial realistic-latent representations from lower-quality images result in over-smoothing in the final output. To address this, we introduce a Self-Adaptive Guidance (SAG) mechanism. It dynamically computes a reality score, enhancing the sharpness of the realistic latent. These alternating mechanisms collectively achieve artifact-free super-resolution. Extensive experiments demonstrate the superiority of our method, delivering detailed artifact-free high-resolution images while reducing sampling steps by 2X. We release our code at https://github.com/ProAirVerse/Self-Adaptive-Guidance-Diffusion.git.
Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.
Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large scenes poses challenges due to limited video memory, long optimization time, and noticeable appearance variations. To address these challenges, we present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting. We propose a progressive partitioning strategy to divide a large scene into multiple cells, where the training cameras and point cloud are properly distributed with an airspace-aware visibility criterion. These cells are merged into a complete scene after parallel optimization. We also introduce decoupled appearance modeling into the optimization process to reduce appearance variations in the rendered images. Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets, enabling fast optimization and high-fidelity real-time rendering.
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present "PanGu-Draw", a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce "Coop-Diffusion", an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model is released on the Ascend platform. Project page: $\href{https://pangu-draw.github.io}{this~https~URL}$
3D generation has raised great attention in recent years. With the success of text-to-image diffusion models, the 2D-lifting technique becomes a promising route to controllable 3D generation. However, these methods tend to present inconsistent geometry, which is also known as the Janus problem. We observe that the problem is caused mainly by two aspects, i.e., viewpoint bias in 2D diffusion models and overfitting of the optimization objective. To address it, we propose a two-stage 2D-lifting framework, namely DreamControl, which optimizes coarse NeRF scenes as 3D self-prior and then generates fine-grained objects with control-based score distillation. Specifically, adaptive viewpoint sampling and boundary integrity metric are proposed to ensure the consistency of generated priors. The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures. DreamControl can generate high-quality 3D content in terms of both geometry consistency and texture fidelity. Moreover, our control-based optimization guidance is applicable to more downstream tasks, including user-guided generation and 3D animation. The project page is available at https://github.com/tyhuang0428/DreamControl.
Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image editing, while downstream video synthesis tasks are less explored for several reasons. First, it requires huge memory and compute overhead to train a video generation foundation model. Even with video foundation models, additional costly training is still required for downstream video synthesis tasks. Second, although some works extend image diffusion models into videos in a training-free manner, temporal consistency cannot be well kept. Finally, these adaption methods are specifically designed for one task and fail to generalize to different downstream video synthesis tasks. To mitigate these issues, we propose a training-free general-purpose video synthesis framework, coined as BIVDiff, via bridging specific image diffusion models and general text-to-video foundation diffusion models. Specifically, we first use an image diffusion model (like ControlNet, Instruct Pix2Pix) for frame-wise video generation, then perform Mixed Inversion on the generated video, and finally input the inverted latents into the video diffusion model for temporal smoothing. Decoupling image and video models enables flexible image model selection for different purposes, which endows the framework with strong task generalization and high efficiency. To validate the effectiveness and general use of BIVDiff, we perform a wide range of video generation tasks, including controllable video generation video editing, video inpainting and outpainting. Our project page is available at https://bivdiff.github.io.
Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation models. Nevertheless, these methods often result in either low fidelity or flickering over time due to their limitation to shallow image guidance and poor temporal consistency. To tackle these problems, we propose a high-fidelity image-to-video generation method by devising a frame retention branch on the basis of a pre-trained video diffusion model, named DreamVideo. Instead of integrating the reference image into the diffusion process in a semantic level, our DreamVideo perceives the reference image via convolution layers and concatenate the features with the noisy latents as model input. By this means, the details of the reference image can be preserved to the greatest extent. In addition, by incorporating double-condition classifier-free guidance, a single image can be directed to videos of different actions by providing varying prompt texts. This has significant implications for controllable video generation and holds broad application prospects. We conduct comprehensive experiments on the public dataset, both quantitative and qualitative results indicate that our method outperforms the state-of-the-art method. Especially for fidelity, our model has powerful image retention ability and result in high FVD in UCF101 compared to other image-to-video models. Also, precise control can be achieved by giving different text prompts. Further details and comprehensive results of our model will be presented in https://anonymous0769.github.io/DreamVideo/.
Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics. Project page can be found at https://sites.google.com/view/smtnet.
Estimating 3D rotations is a common procedure for 3D computer vision. The accuracy depends heavily on the rotation representation. One form of representation -- rotation matrices -- is popular due to its continuity, especially for pose estimation tasks. The learning process usually incorporates orthogonalization to ensure orthonormal matrices. Our work reveals, through gradient analysis, that common orthogonalization procedures based on the Gram-Schmidt process and singular value decomposition will slow down training efficiency. To this end, we advocate removing orthogonalization from the learning process and learning unorthogonalized `Pseudo' Rotation Matrices (PRoM). An optimization analysis shows that PRoM converges faster and to a better solution. By replacing the orthogonalization incorporated representation with our proposed PRoM in various rotation-related tasks, we achieve state-of-the-art results on large-scale benchmarks for human pose estimation.