With the development of multimedia applications, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond user interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; however, there exist semantic gaps among multimodal content features and ID features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In this paper, we first systematically investigate the misalignment issue in multimodal recommendations, and propose a solution named AlignRec. In AlignRec, the recommendation objective is decomposed into three alignments, namely alignment within contents, alignment between content and categorical ID, and alignment between users and items. Each alignment is characterized by a specific objective function and is integrated into our multimodal recommendation framework. To effectively train our AlignRec, we propose starting from pre-training the first alignment to obtain unified multimodal features and subsequently training the following two alignments together with these features as input. As it is essential to analyze whether each multimodal feature helps in training, we design three new classes of metrics to evaluate intermediate performance. Our extensive experiments on three real-world datasets consistently verify the superiority of AlignRec compared to nine baselines. We also find that the multimodal features generated by AlignRec are better than currently used ones, which are to be open-sourced.
Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for machine learning. Despite progress in generating 2D medical images, the complex domain of clinical video generation has largely remained untapped.This paper introduces \model, an innovative approach to generate medical videos that simulate clinical endoscopy scenes. We present a novel generative model design that integrates a meticulously crafted spatial-temporal video transformer with advanced 2D vision foundation model priors, explicitly modeling spatial-temporal dynamics during video generation. We also pioneer the first public benchmark for endoscopy simulation with video generation models, adapting existing state-of-the-art methods for this endeavor.Endora demonstrates exceptional visual quality in generating endoscopy videos, surpassing state-of-the-art methods in extensive testing. Moreover, we explore how this endoscopy simulator can empower downstream video analysis tasks and even generate 3D medical scenes with multi-view consistency. In a nutshell, Endora marks a notable breakthrough in the deployment of generative AI for clinical endoscopy research, setting a substantial stage for further advances in medical content generation. For more details, please visit our project page: https://endora-medvidgen.github.io/.
Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning to reverse the process of gradually adding noise to images, allowing them to generate high-quality samples from a complex distribution. In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field. We delve into a thorough analysis and categorization of these works from multiple perspectives, including learning strategies, user-input conditions, and the array of specific editing tasks that can be accomplished. In addition, we pay special attention to image inpainting and outpainting, and explore both earlier traditional context-driven and current multimodal conditional methods, offering a comprehensive analysis of their methodologies. To further evaluate the performance of text-guided image editing algorithms, we propose a systematic benchmark, EditEval, featuring an innovative metric, LMM Score. Finally, we address current limitations and envision some potential directions for future research. The accompanying repository is released at https://github.com/SiatMMLab/Awesome-Diffusion-Model-Based-Image-Editing-Methods.
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving nature of sentence prefixes during the pre-training phase, existing zero-shot CoT prompting methods that employ identical CoT prompting across all task instances may not be optimal. In this paper, we introduce a novel zero-shot prompting method that leverages evolutionary algorithms to generate diverse promptings for LLMs dynamically. Our approach involves initializing two CoT promptings, performing evolutionary operations based on LLMs to create a varied set, and utilizing the LLMs to select a suitable CoT prompting for a given problem. Additionally, a rewriting operation, guided by the selected CoT prompting, enhances the understanding of the LLMs about the problem. Extensive experiments conducted across ten reasoning datasets demonstrate the superior performance of our proposed method compared to current zero-shot CoT prompting methods on GPT-3.5-turbo and GPT-4. Moreover, in-depth analytical experiments underscore the adaptability and effectiveness of our method in various reasoning tasks.
Reconstructing deformable tissues from endoscopic stereo videos is essential in many downstream surgical applications. However, existing methods suffer from slow inference speed, which greatly limits their practical use. In this paper, we introduce EndoGaussian, a real-time surgical scene reconstruction framework that builds on 3D Gaussian Splatting. Our framework represents dynamic surgical scenes as canonical Gaussians and a time-dependent deformation field, which predicts Gaussian deformations at novel timestamps. Due to the efficient Gaussian representation and parallel rendering pipeline, our framework significantly accelerates the rendering speed compared to previous methods. In addition, we design the deformation field as the combination of a lightweight encoding voxel and an extremely tiny MLP, allowing for efficient Gaussian tracking with a minor rendering burden. Furthermore, we design a holistic Gaussian initialization method to fully leverage the surface distribution prior, achieved by searching informative points from across the input image sequence. Experiments on public endoscope datasets demonstrate that our method can achieve real-time rendering speed (195 FPS real-time, 100$\times$ gain) while maintaining the state-of-the-art reconstruction quality (35.925 PSNR) and the fastest training speed (within 2 min/scene), showing significant promise for intraoperative surgery applications. Code is available at: \url{https://yifliu3.github.io/EndoGaussian/}.
Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects.
The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained textual descriptions. To better perceive and generate human-human interactions, we propose Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures. The dataset includes ~11K interaction sequences and more than 8.1M frames. We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects. Based on the elaborate annotations, we propose a unified benchmark composed of 4 categories of downstream tasks from both the perceptual and generative directions. Extensive experiments and comprehensive analysis show that Inter-X serves as a testbed for promoting the development of versatile human-human interaction analysis. Our dataset and benchmark will be publicly available for research purposes.
With the development of spaceflight and the exploration of extraterrestrial planets, exoplanet crater detection has gradually gained attention. However, with the current scarcity of relevant datasets, high sample background complexity, and large inter-domain differences, few existing detection models can achieve good robustness and generalization across domains by training on data with more background interference. To obtain a better robust model with better cross-domain generalization in the presence of poor data quality, we propose the SCPQ model, in which we first propose a method for fusing shallow information using attention mechanism (FSIAM), which utilizes feature maps fused with deep convolved feature maps after fully extracting the global sensory field of shallow information via the attention mechanism module, which can fully fit the data to obtain a better sense of the domain in the presence of poor data, and thus better multiscale adaptability. Secondly, we propose a pseudo-label and data augment strategy (PDAS) and a smooth hard example mining (SHEM) loss function to improve cross-domain performance. PDAS adopts high-quality pseudo-labeled data from the target domain to the finetune model, and adopts different strong and weak data enhancement strategies for different domains, which mitigates the different distribution of information inherent in the source and target domains, and obtains a better generalization effect. Meanwhile, our proposed SHEM loss function can solve the problem of poor robustness of hard examples due to partial background interference learning during the training process. The SHEM loss function can smooth this interference and has generalization while learning hard examples. Experimental results show that we achieved better performance on the DACD dataset and improved the Recall of cross-domain detection by 24.04\% over baseline.
Recent methods for dynamic human reconstruction have attained promising reconstruction results. Most of these methods rely only on RGB color supervision without considering explicit geometric constraints. This leads to existing human reconstruction techniques being more prone to overfitting to color and causes geometrically inherent ambiguities, especially in the sparse multi-view setup. Motivated by recent advances in the field of monocular geometry prediction, we consider the geometric constraints of estimated depth and normals in the learning of neural implicit representation for dynamic human reconstruction. As a geometric regularization, this provides reliable yet explicit supervision information, and improves reconstruction quality. We also exploit several beneficial physical priors, such as adding noise into view direction and maximizing the density on the human surface. These priors ensure the color rendered along rays to be robust to view direction and reduce the inherent ambiguities of density estimated along rays. Experimental results demonstrate that depth and normal cues, predicted by human-specific monocular estimators, can provide effective supervision signals and render more accurate images. Finally, we also show that the proposed physical priors significantly reduce overfitting and improve the overall quality of novel view synthesis. Our code is available at:~\href{https://github.com/PRIS-CV/HumanRecon}{https://github.com/PRIS-CV/HumanRecon}.
Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for future explorations.