We introduce Motion-I2V, a novel framework for consistent and controllable image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages with explicit motion modeling. For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels. For the second stage, we propose motion-augmented temporal attention to enhance the limited 1-D temporal attention in video latent diffusion models. This module can effectively propagate reference image's feature to synthesized frames with the guidance of predicted trajectories from the first stage. Compared with existing methods, Motion-I2V can generate more consistent videos even at the presence of large motion and viewpoint variation. By training a sparse trajectory ControlNet for the first stage, Motion-I2V can support users to precisely control motion trajectories and motion regions with sparse trajectory and region annotations. This offers more controllability of the I2V process than solely relying on textual instructions. Additionally, Motion-I2V's second stage naturally supports zero-shot video-to-video translation. Both qualitative and quantitative comparisons demonstrate the advantages of Motion-I2V over prior approaches in consistent and controllable image-to-video generation.
相關內容
Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fall short of generating images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning and merging. First, SELMA leverages an LLM's in-context learning capability to generate multiple datasets of text prompts that can teach different skills, and then generates the images with a T2I model based on the prompts. Next, SELMA adapts the T2I model to the new skills by learning multiple single-skill LoRA (low-rank adaptation) experts followed by expert merging. Our independent expert fine-tuning specializes multiple models for different skills, and expert merging helps build a joint multi-skill T2I model that can generate faithful images given diverse text prompts, while mitigating the knowledge conflict from different datasets. We empirically demonstrate that SELMA significantly improves the semantic alignment and text faithfulness of state-of-the-art T2I diffusion models on multiple benchmarks (+2.1% on TIFA and +6.9% on DSG), human preference metrics (PickScore, ImageReward, and HPS), as well as human evaluation. Moreover, fine-tuning with image-text pairs auto-collected via SELMA shows comparable performance to fine-tuning with ground truth data. Lastly, we show that fine-tuning with images from a weaker T2I model can help improve the generation quality of a stronger T2I model, suggesting promising weak-to-strong generalization in T2I models.
High Dynamic Range (HDR) imaging aims to generate an artifact-free HDR image with realistic details by fusing multi-exposure Low Dynamic Range (LDR) images. Caused by large motion and severe under-/over-exposure among input LDR images, HDR imaging suffers from ghosting artifacts and fusion distortions. To address these critical issues, we propose an HDR Transformer Deformation Convolution (HDRTransDC) network to generate high-quality HDR images, which consists of the Transformer Deformable Convolution Alignment Module (TDCAM) and the Dynamic Weight Fusion Block (DWFB). To solve the ghosting artifacts, the proposed TDCAM extracts long-distance content similar to the reference feature in the entire non-reference features, which can accurately remove misalignment and fill the content occluded by moving objects. For the purpose of eliminating fusion distortions, we propose DWFB to spatially adaptively select useful information across frames to effectively fuse multi-exposed features. Extensive experiments show that our method quantitatively and qualitatively achieves state-of-the-art performance.
In this work, we present RadCloud, a novel real time framework for directly obtaining higher-resolution lidar-like 2D point clouds from low-resolution radar frames on resource-constrained platforms commonly used in unmanned aerial and ground vehicles (UAVs and UGVs, respectively); such point clouds can then be used for accurate environmental mapping, navigating unknown environments, and other robotics tasks. While high-resolution sensing using radar data has been previously reported, existing methods cannot be used on most UAVs, which have limited computational power and energy; thus, existing demonstrations focus on offline radar processing. RadCloud overcomes these challenges by using a radar configuration with 1/4th of the range resolution and employing a deep learning model with 2.25x fewer parameters. Additionally, RadCloud utilizes a novel chirp-based approach that makes obtained point clouds resilient to rapid movements (e.g., aggressive turns or spins), which commonly occur during UAV flights. In real-world experiments, we demonstrate the accuracy and applicability of RadCloud on commercially available UAVs and UGVs, with off-the-shelf radar platforms on-board.
The vSPACE experimental proof-of-concept (PoC) on the TrueElect[Anon][Creds] protocol presents a novel approach to secure, private, and scalable elections, extending the TrueElect and ElectAnon protocols with the integration of AnonCreds SSI (Self-Sovereign Identity). Such a protocol PoC is situated within a Zero-Trust Architecture (ZTA) and leverages confidential computing, continuous authentication, multi-party computation (MPC), and well-architected framework (WAF) principles to address the challenges of cybersecurity, privacy, and trust over IP (ToIP) protection. Employing a Kubernetes confidential cluster within an Enterprise-Scale Landing Zone (ESLZ), vSPACE integrates Distributed Ledger Technology (DLT) for immutable and certifiable audit trails. The Infrastructure as Code (IaC) model ensures rapid deployment, consistent management, and adherence to security standards, making vSPACE a future-proof solution for digital voting systems.
We present DiffChat, a novel method to align Large Language Models (LLMs) to "chat" with prompt-as-input Text-to-Image Synthesis (TIS) models (e.g., Stable Diffusion) for interactive image creation. Given a raw prompt/image and a user-specified instruction, DiffChat can effectively make appropriate modifications and generate the target prompt, which can be leveraged to create the target image of high quality. To achieve this, we first collect an instruction-following prompt engineering dataset named InstructPE for the supervised training of DiffChat. Next, we propose a reinforcement learning framework with the feedback of three core criteria for image creation, i.e., aesthetics, user preference, and content integrity. It involves an action-space dynamic modification technique to obtain more relevant positive samples and harder negative samples during the off-policy sampling. Content integrity is also introduced into the value estimation function for further improvement of produced images. Our method can exhibit superior performance than baseline models and strong competitors based on both automatic and human evaluations, which fully demonstrates its effectiveness.
We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We tackle this problem differently by formulating the task as an image translation problem steered by text and motion magnitude prompts, as shown in teaser fig. To ensure that the model adheres to motion guidance, we propose a new motion-guided warping module to spatially transform the features of the source image conditioned on the two types of prompts. Furthermore, we introduce a perceptual loss to ensure the transformed feature map remains within the same space as the target image, ensuring content consistency and coherence. In preparation for the model training, we meticulously curated data by extracting coherent image frames from the TGIF video-caption dataset, which provides rich information about the temporal changes of subjects. After pretraining, we apply our model in a zero-shot manner to a number of video datasets. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our model -- it not only captures the semantic prompt from text but also the spatial ones from motion guidance. We train all our models using a single node of 16xV100 GPUs. Code, dataset and models are made public at: //hiteshk03.github.io/Pix2Gif/.
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks, including document question answering (DocVQA) and scene text analysis. Our approach introduces enhancement across several dimensions: by adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability and minimize hallucinations. Additionally, TextMonkey can be finetuned to gain the ability to comprehend commands for clicking screenshots. Overall, our method notably boosts performance across various benchmark datasets, achieving increases of 5.2%, 6.9%, and 2.8% in Scene Text-Centric VQA, Document Oriented VQA, and KIE, respectively, especially with a score of 561 on OCRBench, surpassing prior open-sourced large multimodal models for document understanding. Code will be released at //github.com/Yuliang-Liu/Monkey.
ProMoAI is a novel tool that leverages Large Language Models (LLMs) to automatically generate process models from textual descriptions, incorporating advanced prompt engineering, error handling, and code generation techniques. Beyond automating the generation of complex process models, ProMoAI also supports process model optimization. Users can interact with the tool by providing feedback on the generated model, which is then used for refining the process model. ProMoAI utilizes the capabilities LLMs to offer a novel, AI-driven approach to process modeling, significantly reducing the barrier to entry for users without deep technical knowledge in process modeling.
This paper presents a CLIP-based unsupervised learning method for annotation-free multi-label image classification, including three stages: initialization, training, and inference. At the initialization stage, we take full advantage of the powerful CLIP model and propose a novel approach to extend CLIP for multi-label predictions based on global-local image-text similarity aggregation. To be more specific, we split each image into snippets and leverage CLIP to generate the similarity vector for the whole image (global) as well as each snippet (local). Then a similarity aggregator is introduced to leverage the global and local similarity vectors. Using the aggregated similarity scores as the initial pseudo labels at the training stage, we propose an optimization framework to train the parameters of the classification network and refine pseudo labels for unobserved labels. During inference, only the classification network is used to predict the labels of the input image. Extensive experiments show that our method outperforms state-of-the-art unsupervised methods on MS-COCO, PASCAL VOC 2007, PASCAL VOC 2012, and NUS datasets and even achieves comparable results to weakly supervised classification methods.
Large language models (LLMs) have made significant advancements in code-related tasks, yet many LLMs treat code as simple sequences, neglecting its structured nature. We introduce AST-T5, a novel pretraining paradigm that leverages the Abstract Syntax Tree (AST) for enhanced code generation, transpilation, and understanding. Using dynamic programming, our AST-Aware Segmentation retains code structure, while our AST-Aware Span Corruption objective equips the model to reconstruct various code structures. Unlike other models, AST-T5 avoids intricate program analyses or architectural changes, so it integrates seamlessly with any encoder-decoder Transformer. Evaluations show that AST-T5 consistently outperforms similar-sized LMs across various code-related tasks. Structure-awareness makes AST-T5 particularly powerful in code-to-code tasks, surpassing CodeT5 by 2 points in exact match score for the Bugs2Fix task and by 3 points in exact match score for Java-C# Transpilation in CodeXGLUE. Our code and model are publicly available at //github.com/gonglinyuan/ast_t5.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191