Generating high-quality whole-body human object interaction motion sequences is becoming increasingly important in various fields such as animation, VR/AR, and robotics. The main challenge of this task lies in determining the level of involvement of each hand given the complex shapes of objects in different sizes and their different motion trajectories, while ensuring strong grasping realism and guaranteeing the coordination of movement in all body parts. Contrasting with existing work, which either generates human interaction motion sequences without detailed hand grasping poses or only models a static grasping pose, we propose a simple yet effective framework that jointly models the relationship between the body, hands, and the given object motion sequences within a single diffusion model. To guide our network in perceiving the object's spatial position and learning more natural grasping poses, we introduce novel contact-aware losses and incorporate a data-driven, carefully designed guidance. Experimental results demonstrate that our approach outperforms the state-of-the-art method and generates plausible results.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
We present InstantSticker, a disentangled reconstruction pipeline based on Image-Based Lighting (IBL), which focuses on highly realistic decal blending, simulates stickers attached to the reconstructed surface, and allows for instant editing and real-time rendering. To achieve stereoscopic impression of the decal, we introduce shadow factor into IBL, which can be adaptively optimized during training. This allows the shadow brightness of surfaces to be accurately decomposed rather than baked into the diffuse color, ensuring that the edited texture exhibits authentic shading. To address the issues of warping and blurriness in previous methods, we apply As-Rigid-As-Possible (ARAP) parameterization to pre-unfold a specified area of the mesh and use the local UV mapping combined with a neural texture map to enhance the ability to express high-frequency details in that area. For instant editing, we utilize the Disney BRDF model, explicitly defining material colors with 3-channel diffuse albedo. This enables instant replacement of albedo RGB values during the editing process, avoiding the prolonged optimization required in previous approaches. In our experiment, we introduce the Ratio Variance Warping (RVW) metric to evaluate the local geometric warping of the decal area. Extensive experimental results demonstrate that our method surpasses previous decal blending methods in terms of editing quality, editing speed and rendering speed, achieving the state-of-the-art.
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
PDF ↗Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment, owing to insufficient quality and quantity of training videos. In this paper, we introduce VideoElevator, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I. Different from conventional T2V sampling (i.e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating. Specifically, temporal motion refining uses encapsulated T2V to enhance temporal consistency, followed by inverting to the noise distribution required by T2I. Then, spatial quality elevating harnesses inflated T2I to directly predict less noisy latent, adding more photo-realistic details. We have conducted experiments in extensive prompts under the combination of various T2V and T2I. The results show that VideoElevator not only improves the performance of T2V baselines with foundational T2I, but also facilitates stylistic video synthesis with personalized T2I. Please watch all videos in supplementary materials for better view.
Controllable image semantic understanding tasks, such as captioning or segmentation, necessitate users to input a prompt (e.g., text or bounding boxes) to predict a unique outcome, presenting challenges such as high-cost prompt input or limited information output. This paper introduces a new task ``Image Collaborative Segmentation and Captioning'' (SegCaptioning), which aims to translate a straightforward prompt, like a bounding box around an object, into diverse semantic interpretations represented by (caption, masks) pairs, allowing flexible result selection by users. This task poses significant challenges, including accurately capturing a user's intention from a minimal prompt while simultaneously predicting multiple semantically aligned caption words and masks. Technically, we propose a novel Scene Graph Guided Diffusion Model that leverages structured scene graph features for correlated mask-caption prediction. Initially, we introduce a Prompt-Centric Scene Graph Adaptor to map a user's prompt to a scene graph, effectively capturing his intention. Subsequently, we employ a diffusion process incorporating a Scene Graph Guided Bimodal Transformer to predict correlated caption-mask pairs by uncovering intricate correlations between them. To ensure accurate alignment, we design a Multi-Entities Contrastive Learning loss to explicitly align visual and textual entities by considering inter-modal similarity, resulting in well-aligned caption-mask pairs. Extensive experiments conducted on two datasets demonstrate that SGDiff achieves superior performance in SegCaptioning, yielding promising results for both captioning and segmentation tasks with minimal prompt input.
PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack
PDF ↗Deep neural networks (DNNs) have achieved remarkable success in widespread applications. Meanwhile, its vulnerability towards carefully crafted adversarial attacks captures special attention. Not only adversarial perturbations in digital space will fool the target DNNs-based detectors making a wrong decision, but also actually printed patches can be camouflaged to defeat detectors in physical space. In particular, multi-view physical adversarial attacks pose a more serious threat to practical scenarios. The existing attacks are still challenged in three aspects, i.e., high-cost data augmentation, attack performance gap between digital and physical space, and low attack transferability across DNNs. To overcome the challenges, we introduce PhyCamo, a robust physical camouflage framework based on contrastive learning that distinguishes itself from prior research in various critical ways: (1) data augmentation - it utilizes the diffusion model for data augmentation to efficiently simulate sophisticated physical dynamics in real-world; (2) robustness - it leverages contrastive learning to optimize physical camouflage against encoders with the state-of-the-art (SOTA) attack performance; (3) transferability - it mitigates the model-specific noise in the optimization by adopting diverse input methods, thereby amplifying the transferability between models. Extensive experiments are carried out on a car dataset, a tank dataset, and a pedestrian dataset, comparing with 6 classic multi-view physical adversarial attacks in both digital and physical spaces. The results demonstrate PhyCamo’s superior performance. For instance, it generates more effective physical camouflage (with higher attack success rate~×1.26 and reduce the model's average precision by 55%). PhyCamo can also help to improve the robustness of detectors through adversarial training, which contributes to the application of deep neural networks in the field of security sensitivity.
Generative models are widely used to produce synthetic images with annotations, alleviating the burden of image collection and annotation for training deep visual models. However, challenges such as limited image diversity, noisy pseudo labels, and domain gaps between synthetic and real images often undermine their effectiveness in downstream visual tasks. This paper introduces the Iterative Self-Training with Class-Aware Text-to-Image Synthesis (IST-CATS) framework, which addresses these challenges by integrating a class-aware text-to-image synthesis (CATS) component with an iterative self-training (IST) strategy. CATS innovatively introduces a class-aware chain approach to generate detailed descriptions. These descriptions act as prompts for a diffusion model, enabling the creation of a diverse of images accompanied by distinguishable objects against the background. The generated images can be easily pseudo-labeled by an unsupervised instance segmentation method, and then noisy pseudo labels can be effectively purified by a novel feature similarity-based filtering mechanism. The generated images underpin our IST, which progressively enhances vision models and refines pseudo labels through self-training and our proposed label filtering strategy (LabFilt). LabFilt meticulously improves the quality of pseudo labels by employing class-adaptive techniques at both the pixel and object levels, ensuring refined pseudo-label accuracy. IST-CATS demonstrates superior performance in object detection and semantic segmentation compared to traditional synthetic and semi/weakly-supervised methods, effectively addressing data collection and annotation challenges.
Zero-shot anomaly detection (ZSAD) aims to identify anomalies in new classes of images, and it’s vital in industry and other fields. Most current methods are based on the multimodal models CLIP and SAM, which have prior knowledge to assist model training, but they are highly dependent on the input of the prompts and their accuracy. We found that some diffusion model-based anomaly detection methods generate a large amount of semantic information and are very valuable for the ZSAD task. Therefore, we propose a diffusion model based zero-shot anomaly detection method, DZAD, and no additional prompt input is required. First, we propose the first diffusion-based zero-shot anomaly detection framework, which uses the proposed multi-timestep noise features extraction method to achieve anomaly detection in the denoising process of a latent space diffusion model with a semantic-guided (SG) network. Second, based on the detection results, we proposed a two-branch feature extractor for anomaly maps at different scales. Third, based on the difference between the anomaly detection task and other general image detection tasks, we propose a noise feature weight function for the diffusion model in the zero-shot anomaly detection task. Comparing with 7 recently state-of-the-art (SOTA) methods on MVTec AD and VisA datasets and analysis of the role of each component in ablation studies. The experiments demonstrate the validity of the method beyond the existing methods.
Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views
PDF ↗Inferring 3D structures from sparse, unposed observations is challenging due to its unconstrained nature. Recent methods propose to predict implicit representations directly from unposed inputs in a data-driven manner, achieving promising results. However, these methods do not utilize geometric priors and cannot hallucinate the appearance of unseen regions, thus making it challenging to reconstruct fine geometric and textural details. To tackle this challenge, our key idea is to reformulate this ill-posed problem as conditional novel view synthesis, aiming to generate complete observations from limited input views to facilitate reconstruction. With complete observations, the poses of the input views can be easily recovered and further used to optimize the reconstructed object. To this end, we propose a novel pipeline, Pragmatist. First, we generate a complete observation of the object via a multiview conditional diffusion model. Then, we use a feed-forward large reconstruction model to obtain the reconstructed mesh. To further improve the reconstruction quality, we recover the poses of input views by inverting the obtained 3D representations and further optimize the texture using detailed input views. Unlike previous approaches, our pipeline improves reconstruction by efficiently leveraging unposed inputs and generative priors, circumventing the direct resolution of highly ill-posed problems. Extensive experiments show that our approach achieves promising performance in several benchmarks.
Multi-modal salient object detection (SOD) through the integration of additional data such as depth or thermal information has become a significant task in computer vision during recent years. Traditionally, the challenges of identifying salient objects in RGB, RGB-D (Depth), and RGB-T (Thermal) images are tackled separately. However, without intricate cross-modal fusion strategies, such approaches struggle to effectively integrate multi-modal information, often resulting in poorly defined object edges or overconfident inaccurate predictions. Recent studies have shown that designing a unified end-to-end framework to handle all three types of SOD tasks simultaneously is both necessary and difficult. To address this need, we propose a novel approach that treats multi-modal SOD as a conditional mask generation task utilizing diffusion models. We introduce DiMSOD, which enables the concurrent use of local (depth maps, thermal maps) and global controls (original images) within a unified model for progressive denoising and refined prediction. DiMSOD is efficient, only requiring fine-tuning of our newly introduced modules on the existing stable diffusion, which not only reduces the fine-tuning cost, making it more viable for practical use, but also enhances the integration of multi-modal conditional controls. Specifically, we have developed modules including SOD-ControlNet, Feature Adaptive Network (FAN), and Feature Injection Attention Network (FIAN) to enhance the model's performance. Extensive experiments demonstrate that DiMSOD efficiently detects salient objects across RGB, RGB-D, and RGB-T datasets, achieving superior performance compared to previous well-established methods.
View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
PDF ↗View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom focused on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models' VTR is to produce data with more view transformations and add them to model training. Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. Directly deploying these models at inference consumes heavy computation resources and their robustness to view transformations is not guaranteed either. To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors' spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models' robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods.
Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to produce photorealistic images/videos, which is computationally expensive. Unlike previous methods that design ``one-size-fits-all'' approaches for speed up, we argue denoising steps should be sample-specific conditioned on the richness of input texts. To this end, we introduce AdaDiff, a lightweight framework designed to learn instance-specific step usage policies, which are then used by the diffusion model for generation. AdaDiff is optimized using a policy gradient method to maximize a carefully designed reward function, balancing inference time and generation quality. We conduct experiments on three image generation and two video generation benchmarks and demonstrate that our approach achieves similar visual quality compared to the baseline using a fixed 50 denoising steps while reducing inference time by at least 33%, going as high as 40%. Furthermore, our method can be used on top of other acceleration methods to provide further speed benefits. Lastly, qualitative analysis shows that AdaDiff allocates more steps to more informative prompts and fewer steps to simpler prompts.
Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model’s understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing and colors.
Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning
PDF ↗The excellent performance of diffusion models in image generation is always accompanied by overlarge computation costs, which have prevented the application of diffusion models in edge devices and interactive applications. Previous works mainly focus on using fewer sampling steps and compressing the denoising network of diffusion models, while this paper proposes to accelerate diffusion models by introducing SiTo, a similarity-based token pruning method that adaptive prunes the redundant tokens in the input data. SiTo is designed to maximize the similarity between model prediction with and without token pruning by using cheap and hardware-friendly operations, leading to significant acceleration ratios without performance drop, and even sometimes improvements in the generation quality. For instance, the zero-shot evaluation shows SiTo leads to 1.90x and 1.75x acceleration on COCO30K and ImageNet with 1.33 and 1.15 FID reduction at the same time. Besides, SiTo has no training requirements and does not require any calibration data, making it plug-and-play in real-world applications.
Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and accelerates diffusion models without retraining, but it inevitably introduces additional quantization noise, resulting in mean and variance deviations. In this work, we propose D2-DPM, a dual denoising mechanism aimed at precisely mitigating the adverse effects of quantization noise on the noise estimation network. Specifically, we first unravel the impact of quantization noise on the sampling equation into two components: the mean deviation and the variance deviation. The mean deviation alters the drift coefficient of the sampling equation, influencing the trajectory trend, while the variance deviation magnifies the diffusion coefficient, impacting the convergence of the sampling trajectory. The proposed D2-DPM is thus devised to denoise the quantization noise at each time step, and then denoise the noisy sample through the inverse diffusion iterations. Experimental results demonstrate that D2-DPM achieves superior generation quality, yielding a 1.42 lower FID than the full-precision model while achieving 3.99x compression and 11.67x bit-operation acceleration.
ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model
PDF ↗Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and knowledge-intensive. Existing generative methods for CD data synthesis show competitive potential in addressing this issue but still face the following limitations: 1) difficulty in flexibly controlling change events, 2) dependence on additional data to train the data generators, 3) focus on specific change detection tasks. To this end, this paper focuses on the semantic CD (SCD) task and develops a multi-temporal SCD data generator ChangeDiff by exploring powerful diffusion models. ChangeDiff innovatively generates change data in two steps: first, it uses text prompts and a text-to-layout (T2L) model to create continuous layouts, and then it employs layout-to-image (L2I) to convert these layouts into images. Specifically, we propose multi-class distribution-guided text prompts (MCDG-TP), allowing for layouts to be generated flexibly through controllable classes and their corresponding ratios. Subsequently, to generalize the T2L model to the proposed MCDG-TP, a class distribution refinement loss is further designed as training supervision. Our generated data shows significant progress in temporal continuity, spatial diversity, and quality realism, empowering change detectors with accuracy and transferability.
We propose a transformation diffusion model for point cloud registration to balance precision and efficiency. Our method formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation, which is represented by quaternion and translation. Specifically, in training stage, object transformation diffuses from ground-truth transformation to random distribution, and the model learns to reverse this noising process. In sampling stage, the model refines randomly generated transformation to the optimal transformation in a progressive way. We derive the variational bound in closed form for training and provide instantiation of the model. Our diffusion model maps transformation into latent space, and splits the transformation into two components (rotation and translation) based on the fact that they belong to different solution spaces. In addition, our work provides the following crucial findings: (i) Point cloud registration, one of the representative discriminative tasks, can be solved by a generative way and mapped into latent space to obtain new unified probabilistic formulation. (ii) Our model, Transformation Diffusion Model (TDM) can be a plug-and-play agent for point cloud registration, making our method applicable to different deep registration networks. Experimental results on synthetic and real-world datasets demonstrate that, in correspondence-free and correspondence-based scenarios, TDM can both achieve exceeding 60% performance improvements and higher efficiency simultaneously.
Recent methods using diffusion models have made significant progress in human image generation with various control signals such as pose priors. However, existing efforts are still struggling to generate high-quality images with consistent pose alignment, resulting in unsatisfactory output. In this paper, we propose a framework that delves into the graph relations of pose priors to provide control information for human image generation. The main idea is to establish a graph topological structure between the pose priors and latent representation of diffusion models to capture the intrinsic associations between different pose parts. A Progressive Graph Integrator (PGI) is designed to learn the spatial relationships of the pose priors with the graph structure, adopting a hierarchical strategy within an Adapter to gradually propagate information across different pose parts. Besides, a pose perception loss is introduced based on a pretrained pose estimation network to minimize the pose differences. Extensive qualitative and quantitative experiments conducted on the Human-Art and LAION-Human datasets clearly demonstrate that our model can achieve significant performance improvement over the latest benchmark models.
High-quality, pixel-level annotated datasets are crucial for training deep learning models, while their creation is often labor-intensive, time-consuming, and costly. Generative diffusion models have then gained prominence for producing synthetic datasets, yet existing text-to-data methods struggle with generating complex scenes involving multiple objects and intricate spatial arrangements. To address these limitations, we introduce FlexDataset, a framework that pioneers the composition-to-data (C2D) paradigm. FlexDataset generates high-fidelity synthetic datasets with versatile annotations, tailored for tasks like salient object detection, depth estimation, and segmentation. Leveraging a meticulously designed composition-to-image (C2I) framework, it offers precise positional and categorical control. Our Versatile Annotation Generation (VAG) Plan A further enhances efficiency by exploiting rich latent representations through tuned perception decoders, reducing annotation time by nearly fivefold. FlexDataset allows unlimited generation of customized, multi-instance and multi-category (MIMC) annotated data. Extensive experiments show that FlexDataset sets a new standard in synthetic dataset generation across multiple datasets and tasks, including zero-shot and long-tail scenarios.
VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement
PDF ↗Text-to-image (T2I) diffusion models have achieved remarkable progress in generating realistic images from textual descriptions. However, ensuring consistent high-quality image generation with complete backgrounds, object appearance, and optimal texture rendering remains challenging. This paper presents a novel fine-grained pixel-level image editing method based on pre-trained diffusion models. The proposed dual-branch architecture, consisting of Guidance and Generation branches, employs U-Net Denoisers and Self-Attention mechanisms. An improved DDIM-like inversion method obtains the latent representation, followed by multiple denoising steps. Cross-branch interactions, such as KV Replacement, Classifier Guidance, and Feature Correspondence, enable precise control while preserving image fidelity. The iterative refinement and reconstruction process facilitates finegrained editing control, supporting attribute modification, image outpainting, style transfer, and face synthesis with Clickand-Drag style editing using masks. Experimental results demonstrate the effectiveness of the proposed approach in enhancing the quality and controllability of T2I-generated images, surpassing existing methods while maintaining attractive computational complexity for practical real-world applications.
Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable data representation that facilitates these applications. However, current graph-based methods for scene generation are constrained to text-based inputs and exhibit insufficient adaptability to flexible user inputs, hindering the ability to precisely control object geometry. To address this issue, we propose MMGDreamer, a dual-branch diffusion model for scene generation that incorporates a novel Mixed-Modality Graph, visual enhancement module, and relation predictor. The mixed-modality graph allows object nodes to integrate textual and visual modalities, with optional relationships between nodes. It enhances adaptability to flexible user inputs and enables meticulous control over the geometry of objects in the generated scenes. The visual enhancement module enriches the visual fidelity of text-only nodes by constructing visual representations using text embeddings. Furthermore, our relation predictor leverages node representations to infer absent relationships between nodes, resulting in more coherent scene layouts. Extensive experimental results demonstrate that MMGDreamer exhibits superior control of object geometry, achieving state-of-the-art scene generation performance.