PyTorchKR Papers

최신 논문

총 1,880편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2412.02259공식 코드 · Papers with Code

VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation

Current video generation models excel at generating short clips but still struggle with creating multi-shot, movie-like videos. Existing models trained on large-scale data on the back of rich computational resources are unsurprisingly inadequate for maintaining a logical storyline and visual consistency across multiple shots of a cohesive script since they are often trained with a single-shot objective. To this end, we propose VideoGen-of-Thought (VGoT), a collaborative and training-free architecture designed specifically for multi-shot video generation. VGoT is designed with three goals in mind as follows. Multi-Shot Video Generation: We divide the video generation process into a structured, modular sequence, including (1) Script Generation, which translates a curt story into detailed prompts for each shot; (2) Keyframe Generation, responsible for creating visually consistent keyframes faithful to character portrayals; and (3) Shot-Level Video Generation, which transforms information from scripts and keyframes into shots; (4) Smoothing Mechanism that ensures a consistent multi-shot output. Reasonable Narrative Design: Inspired by cinematic scriptwriting, our prompt generation approach spans five key domains, ensuring logical consistency, character development, and narrative flow across the entire video. Cross-Shot Consistency: We ensure temporal and identity consistency by leveraging identity-preserving (IP) embeddings across shots, which are automatically created from the narrative. Additionally, we incorporate a cross-shot smoothing mechanism, which integrates a reset boundary that effectively combines latent features from adjacent shots, resulting in smooth transitions and maintaining visual coherence throughout the video. Our experiments demonstrate that VGoT surpasses existing video generation methods in producing high-quality, coherent, multi-shot videos.

arXiv:2412.02114

OmniCreator: Self-Supervised Unified Generation with Universal Editing

We introduce OmniCreator, a novel framework that can conduct text-prompted unified (image+video) generation as well as editing all in one place. OmniCreator acquires generative and universal editing capabilities in a self-supervised manner, taking original text-video pairs as conditions while utilizing the same video as a denoising target to learn the semantic correspondence between video and text. During inference, when presented with a text prompt and a video, OmniCreator is capable of generating a target that is faithful to both, achieving a universal editing effect that is unconstrained as opposed to existing editing work that primarily focuses on certain editing types or relies on additional controls (e.g., structural conditions, attention features, or DDIM inversion). On the other hand, when presented with a text prompt only, OmniCreator becomes generative, producing high-quality video as a result of the semantic correspondence learned. Importantly, we found that the same capabilities extend to images as is, making OmniCreator a truly unified framework. Further, due to the lack of existing generative video editing benchmarks, we introduce the OmniBench-99 dataset, designed to evaluate the performance of generative video editing models comprehensively. Extensive experiments demonstrate that OmniCreator exhibits substantial superiority over all other models.

arXiv:2411.18983

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing

While open-source video generation and editing models have made significant progress, individual models are typically limited to specific tasks, failing to meet the diverse needs of users. Effectively coordinating these models can unlock a wide range of video generation and editing capabilities. However, manual coordination is complex and time-consuming, requiring users to deeply understand task requirements and possess comprehensive knowledge of each model's performance, applicability, and limitations, thereby increasing the barrier to entry. To address these challenges, we propose a novel video generation and editing system powered by our Semantic Planning Agent (SPAgent). SPAgent bridges the gap between diverse user intents and the effective utilization of existing generative models, enhancing the adaptability, efficiency, and overall quality of video generation and editing. Specifically, the SPAgent assembles a tool library integrating state-of-the-art open-source image and video generation and editing models as tools. After fine-tuning on our manually annotated dataset, SPAgent can automatically coordinate the tools for video generation and editing, through our novelly designed three-step framework: (1) decoupled intent recognition, (2) principle-guided route planning, and (3) capability-based execution model selection. Additionally, we enhance the SPAgent's video quality evaluation capability, enabling it to autonomously assess and incorporate new video generation and editing models into its tool library without human intervention. Experimental results demonstrate that the SPAgent effectively coordinates models to generate or edit videos, highlighting its versatility and adaptability across various video tasks.

arXiv:2411.18673

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers

Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first principles perspective, uncovering insights that enable precise 3D camera manipulation without compromising synthesis quality. First, we determine that motion induced by camera movements in videos is low-frequency in nature. This motivates us to adjust train and test pose conditioning schedules, accelerating training convergence while improving visual and motion quality. Then, by probing the representations of an unconditional video diffusion transformer, we observe that they implicitly perform camera pose estimation under the hood, and only a sub-portion of their layers contain the camera information. This suggested us to limit the injection of camera conditioning to a subset of the architecture to prevent interference with other video features, leading to a 4x reduction of training parameters, improved training speed, and 10% higher visual quality. Finally, we complement the typical dataset for camera control learning with a curated dataset of 20K diverse, dynamic videos with stationary cameras. This helps the model distinguish between camera and scene motion and improves the dynamics of generated pose-conditioned videos. We compound these findings to design the Advanced 3D Camera Control (AC3D) architecture, the new state-of-the-art model for generative video modeling with camera control.

arXiv:2411.18668

Towards Chunk-Wise Generation for Long Videos

Generating long-duration videos has always been a significant challenge due to the inherent complexity of spatio-temporal domain and the substantial GPU memory demands required to calculate huge size tensors. While diffusion based generative models achieve state-of-the-art performance in video generation task, they are typically trained with predefined video resolutions and lengths. During inference, a noise tensor with specific resolution and length should be specified at first, and the model will perform denoising on the entire video tensor simultaneously, all the frames together. Such approach will easily raise an out-of-memory (OOM) problem when the specified resolution and/or length exceed a certain limit. One of the solutions to this problem is to generate many short video chunks autoregressively with strong inter-chunk spatio-temporal relation and then concatenate them together to form a long video. In this approach, a long video generation task is divided into multiple short video generation subtasks, and the cost of each subtask is reduced to a feasible level. In this paper, we conduct a detailed survey on long video generation with the autoregressive chunk-by-chunk strategy. We address common problems caused by applying short image-to-video models to long video tasks and design an efficient $k$-step search solution to mitigate these problems.

arXiv:2411.19459

Fleximo: Towards Flexible Text-to-Human Motion Video Generation

Current methods for generating human motion videos rely on extracting pose sequences from reference videos, which restricts flexibility and control. Additionally, due to the limitations of pose detection techniques, the extracted pose sequences can sometimes be inaccurate, leading to low-quality video outputs. We introduce a novel task aimed at generating human motion videos solely from reference images and natural language. This approach offers greater flexibility and ease of use, as text is more accessible than the desired guidance videos. However, training an end-to-end model for this task requires millions of high-quality text and human motion video pairs, which are challenging to obtain. To address this, we propose a new framework called Fleximo, which leverages large-scale pre-trained text-to-3D motion models. This approach is not straightforward, as the text-generated skeletons may not consistently match the scale of the reference image and may lack detailed information. To overcome these challenges, we introduce an anchor point based rescale method and design a skeleton adapter to fill in missing details and bridge the gap between text-to-motion and motion-to-video generation. We also propose a video refinement process to further enhance video quality. A large language model (LLM) is employed to decompose natural language into discrete motion sequences, enabling the generation of motion videos of any desired length. To assess the performance of Fleximo, we introduce a new benchmark called MotionBench, which includes 400 videos across 20 identities and 20 motions. We also propose a new metric, MotionScore, to evaluate the accuracy of motion following. Both qualitative and quantitative results demonstrate that our method outperforms existing text-conditioned image-to-video generation methods. All code and model weights will be made publicly available.

arXiv:2411.19324

Trajectory Attention for Fine-grained Video Motion Control

Recent advancements in video generation have been greatly driven by video diffusion models, with camera motion control emerging as a crucial challenge in creating view-customized visual content. This paper introduces trajectory attention, a novel approach that performs attention along available pixel trajectories for fine-grained camera motion control. Unlike existing methods that often yield imprecise outputs or neglect temporal correlations, our approach possesses a stronger inductive bias that seamlessly injects trajectory information into the video generation process. Importantly, our approach models trajectory attention as an auxiliary branch alongside traditional temporal attention. This design enables the original temporal attention and the trajectory attention to work in synergy, ensuring both precise motion control and new content generation capability, which is critical when the trajectory is only partially available. Experiments on camera motion control for images and videos demonstrate significant improvements in precision and long-range consistency while maintaining high-quality generation. Furthermore, we show that our approach can be extended to other video motion control tasks, such as first-frame-guided video editing, where it excels in maintaining content consistency over large spatial and temporal ranges.

arXiv:2411.19108

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly selected timesteps. However, such a strategy neglects the fact that differences among model outputs are not uniform across timesteps, which hinders selecting the appropriate model outputs to cache, leading to a poor balance between inference efficiency and visual quality. In this study, we introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps. Rather than directly using the time-consuming model outputs, TeaCache focuses on model inputs, which have a strong correlation with the modeloutputs while incurring negligible computational cost. TeaCache first modulates the noisy inputs using the timestep embeddings to ensure their differences better approximating those of model outputs. TeaCache then introduces a rescaling strategy to refine the estimated differences and utilizes them to indicate output caching. Experiments show that TeaCache achieves up to 4.41x acceleration over Open-Sora-Plan with negligible (-0.07% Vbench score) degradation of visual quality.

arXiv:2411.19121

MSG score: A Comprehensive Evaluation for Multi-Scene Video Generation

This paper addresses the metrics required for generating multi-scene videos based on a continuous scenario, as opposed to traditional short video generation. Scenario-based videos require a comprehensive evaluation that considers multiple factors such as character consistency, artistic coherence, aesthetic quality, and the alignment of the generated content with the intended prompt. Additionally, in video generation, unlike single images, the movement of characters across frames introduces potential issues like distortion or unintended changes, which must be effectively evaluated and corrected. In the context of probabilistic models like diffusion, generating the desired scene requires repeated sampling and manual selection, akin to how a film director chooses the best shots from numerous takes. We propose a score-based evaluation benchmark that automates this process, enabling a more objective and efficient assessment of these complexities. This approach allows for the generation of high-quality multi-scene videos by selecting the best outcomes based on automated scoring rather than manual inspection.

arXiv:2411.16748

LetsTalk: Latent Diffusion Transformer for Talking Video Synthesis

Portrait image animation using audio has rapidly advanced, enabling the creation of increasingly realistic and expressive animated faces. The challenges of this multimodality-guided video generation task involve fusing various modalities while ensuring consistency in timing and portrait. We further seek to produce vivid talking heads. To address these challenges, we present LetsTalk (LatEnt Diffusion TranSformer for Talking Video Synthesis), a diffusion transformer that incorporates modular temporal and spatial attention mechanisms to merge multimodality and enhance spatial-temporal consistency. To handle multimodal conditions, we first summarize three fusion schemes, ranging from shallow to deep fusion compactness, and thoroughly explore their impact and applicability. Then we propose a suitable solution according to the modality differences of image, audio, and video generation. For portrait, we utilize a deep fusion scheme (Symbiotic Fusion) to ensure portrait consistency. For audio, we implement a shallow fusion scheme (Direct Fusion) to achieve audio-animation alignment while preserving diversity. Our extensive experiments demonstrate that our approach generates temporally coherent and realistic videos with enhanced diversity and liveliness.

arXiv:2411.18375

Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models

The high computational cost and slow inference time are major obstacles to deploying the video diffusion model (VDM) in practical applications. To overcome this, we introduce a new Video Diffusion Model Compression approach using individual content and motion dynamics preserved pruning and consistency loss. First, we empirically observe that deeper VDM layers are crucial for maintaining the quality of \textbf{motion dynamics} e.g., coherence of the entire video, while shallower layers are more focused on \textbf{individual content} e.g., individual frames. Therefore, we prune redundant blocks from the shallower layers while preserving more of the deeper layers, resulting in a lightweight VDM variant called VDMini. Additionally, we propose an \textbf{Individual Content and Motion Dynamics (ICMD)} Consistency Loss to gain comparable generation performance as larger VDM, i.e., the teacher to VDMini i.e., the student. Particularly, we first use the Individual Content Distillation (ICD) Loss to ensure consistency in the features of each generated frame between the teacher and student models. Next, we introduce a Multi-frame Content Adversarial (MCA) Loss to enhance the motion dynamics across the generated video as a whole. This method significantly accelerates inference time while maintaining high-quality video generation. Extensive experiments demonstrate the effectiveness of our VDMini on two important video generation tasks, Text-to-Video (T2V) and Image-to-Video (I2V), where we respectively achieve an average 2.5 $\times$ and 1.4 $\times$ speed up for the I2V method SF-V and the T2V method T2V-Turbo-v2, while maintaining the quality of the generated videos on two benchmarks, i.e., UCF101 and VBench.

arXiv:2411.18281

MotionCharacter: Identity-Preserving and Motion Controllable Human Video Generation

Recent advancements in personalized Text-to-Video (T2V) generation highlight the importance of integrating character-specific identities and actions. However, previous T2V models struggle with identity consistency and controllable motion dynamics, mainly due to limited fine-grained facial and action-based textual prompts, and datasets that overlook key human attributes and actions. To address these challenges, we propose MotionCharacter, an efficient and high-fidelity human video generation framework designed for identity preservation and fine-grained motion control. We introduce an ID-preserving module to maintain identity fidelity while allowing flexible attribute modifications, and further integrate ID-consistency and region-aware loss mechanisms, significantly enhancing identity consistency and detail fidelity. Additionally, our approach incorporates a motion control module that prioritizes action-related text while maintaining subject consistency, along with a dataset, Human-Motion, which utilizes large language models to generate detailed motion descriptions. For simplify user control during inference, we parameterize motion intensity through a single coefficient, allowing for easy adjustments. Extensive experiments highlight the effectiveness of MotionCharacter, demonstrating significant improvements in ID-preserving, high-quality video generation.

arXiv:2411.17911

Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey

In recent years, deepfakes (DFs) have been utilized for malicious purposes, such as individual impersonation, misinformation spreading, and artists style imitation, raising questions about ethical and security concerns. In this survey, we provide a comprehensive review and comparison of passive DF detection across multiple modalities, including image, video, audio, and multi-modal, to explore the inter-modality relationships between them. Beyond detection accuracy, we extend our analysis to encompass crucial performance dimensions essential for real-world deployment: generalization capabilities across novel generation techniques, robustness against adversarial manipulations and postprocessing techniques, attribution precision in identifying generation sources, and resilience under real-world operational conditions. Additionally, we analyze the advantages and limitations of existing datasets, benchmarks, and evaluation metrics for passive DF detection. Finally, we propose future research directions that address these unexplored and emerging issues in the field of passive DF detection. This survey offers researchers and practitioners a comprehensive resource for understanding the current landscape, methodological approaches, and promising future directions in this rapidly evolving field.

arXiv:2411.17221공식 코드 · Papers with Code

AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM

The rapid advancement of large multimodal models (LMMs) has led to the rapid expansion of artificial intelligence generated videos (AIGVs), which highlights the pressing need for effective video quality assessment (VQA) models designed specifically for AIGVs. Current VQA models generally fall short in accurately assessing the perceptual quality of AIGVs due to the presence of unique distortions, such as unrealistic objects, unnatural movements, or inconsistent visual elements. To address this challenge, we first present AIGVQA-DB, a large-scale dataset comprising 36,576 AIGVs generated by 15 advanced text-to-video models using 1,048 diverse prompts. With these AIGVs, a systematic annotation pipeline including scoring and ranking processes is devised, which collects 370k expert ratings to date. Based on AIGVQA-DB, we further introduce AIGV-Assessor, a novel VQA model that leverages spatiotemporal features and LMM frameworks to capture the intricate quality attributes of AIGVs, thereby accurately predicting precise video quality scores and video pair preferences. Through comprehensive experiments on both AIGVQA-DB and existing AIGV databases, AIGV-Assessor demonstrates state-of-the-art performance, significantly surpassing existing scoring or evaluation methods in terms of multiple perceptual quality dimensions.

arXiv:2411.17189

PhysMotion: Physics-Grounded Dynamics From a Single Image

We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing high-quality, physically plausible video generation. By utilizing continuum mechanics-based simulations as a prior knowledge, our approach addresses the limitations of traditional data-driven generative models and result in more consistent physically plausible motions. Our framework begins by reconstructing a feed-forward 3D Gaussian from a single image through geometry optimization. This representation is then time-stepped using a differentiable Material Point Method (MPM) with continuum mechanics-based elastoplasticity models, which provides a strong foundation for realistic dynamics, albeit at a coarse level of detail. To enhance the geometry, appearance and ensure spatiotemporal consistency, we refine the initial simulation using a text-to-image (T2I) diffusion model with cross-frame attention, resulting in a physically plausible video that retains intricate details comparable to the input image. We conduct comprehensive qualitative and quantitative evaluations to validate the efficacy of our method. Our project page is available at: https://supertan0204.github.io/physmotion_website/.

arXiv:2411.17048

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies in maintaining high ID fidelity consistently while preserving the original motion dynamic and semantic following after the identity injection. Current video identity customization methods mainly rely on reconstructing given identity images on text-to-image models, which have a divergent distribution with the T2V model. This process introduces a tuning-inference gap, leading to dynamic and semantic degradation. To tackle this problem, we propose a novel framework, dubbed \textbf{PersonalVideo}, that applies direct supervision on videos synthesized by the T2V model to bridge the gap. Specifically, we introduce a learnable Isolated Identity Adapter to customize the specific identity non-intrusively, which does not comprise the original T2V model's abilities (e.g., motion dynamic and semantic following). With the non-reconstructive identity loss, we further employ simulated prompt augmentation to reduce overfitting by supervising generated results in more semantic scenarios, gaining good robustness even with only a single reference image available. Extensive experiments demonstrate our method's superiority in delivering high identity faithfulness while preserving the inherent video generation qualities of the original T2V model, outshining prior approaches. Notably, our PersonalVideo seamlessly integrates with pre-trained SD components, such as ControlNet and style LoRA, requiring no extra tuning overhead.

arXiv:2411.16804공식 코드 · Papers with Code

InTraGen: Trajectory-controlled Video Generation for Object Interactions

Advances in video generation have significantly improved the realism and quality of created scenes. This has fueled interest in developing intuitive tools that let users leverage video generation as world simulators. Text-to-video (T2V) generation is one such approach, enabling video creation from text descriptions only. Yet, due to the inherent ambiguity in texts and the limited temporal information offered by text prompts, researchers have explored additional control signals like trajectory-guided systems, for more accurate T2V generation. Nonetheless, methods to evaluate whether T2V models can generate realistic interactions between multiple objects are lacking. We introduce InTraGen, a pipeline for improved trajectory-based generation of object interaction scenarios. We propose 4 new datasets and a novel trajectory quality metric to evaluate the performance of the proposed InTraGen. To achieve object interaction, we introduce a multi-modal interaction encoding pipeline with an object ID injection mechanism that enriches object-environment interactions. Our results demonstrate improvements in both visual fidelity and quantitative performance. Code and datasets are available at https://github.com/insait-institute/InTraGen

arXiv:2411.17616공식 코드 · Papers with Code

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference. Through systematic analysis, we identify the absence of long-range feature preservation mechanisms as the root cause of unstable feature propagation and perturbation sensitivity. To this end, we propose Skip-DiT, a novel DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets. Theoretical spectral norm and visualization analysis demonstrate how LSCs stabilize feature dynamics. Skip-DiT architecture and its stabilized dynamic feature enable an efficient statical caching mechanism that reuses deep features across timesteps while updating shallow components. Extensive experiments across image and video generation tasks demonstrate that Skip-DiT achieves: (1) 4.4 times training acceleration and faster convergence, (2) 1.5-2 times inference acceleration without quality loss and high fidelity to original output, outperforming existing DiT caching methods across various quantitative metrics. Our findings establish long-skip connections as critical architectural components for training stable and efficient diffusion transformers.

arXiv:2411.17440공식 코드 · Papers with Code

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving DiT-based control scheme. We propose ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human identity consistent in the generated video. Inspired by prior findings in frequency analysis of diffusion transformers, it employs identity-control signals in the frequency domain, where facial features can be decomposed into low-frequency global features and high-frequency intrinsic features. First, from a low-frequency perspective, we introduce a global facial extractor, which encodes reference images and facial key points into a latent space, generating features enriched with low-frequency information. These features are then integrated into shallow layers of the network to alleviate training challenges associated with DiT. Second, from a high-frequency perspective, we design a local facial extractor to capture high-frequency details and inject them into transformer blocks, enhancing the model's ability to preserve fine-grained features. We propose a hierarchical training strategy to leverage frequency information for identity preservation, transforming a vanilla pre-trained video generation model into an IPT2V model. Extensive experiments demonstrate that our frequency-aware heuristic scheme provides an optimal control solution for DiT-based models. Thanks to this scheme, our ConsisID generates high-quality, identity-preserving videos, making strides towards more effective IPT2V. Code: https://github.com/PKU-YuanGroup/ConsisID.

arXiv:2411.17383

AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation

The automatic generation of anchor-style product promotion videos presents promising opportunities in online commerce, advertising, and consumer engagement. However, this remains a challenging task despite significant advancements in pose-guided human video generation. In addressing this challenge, we identify the integration of human-object interactions (HOI) into pose-guided human video generation as a core issue. To this end, we introduce AnchorCrafter, a novel diffusion-based system designed to generate 2D videos featuring a target human and a customized object, achieving high visual fidelity and controllable interactions. Specifically, we propose two key innovations: the HOI-appearance perception, which enhances object appearance recognition from arbitrary multi-view perspectives and disentangles object and human appearance, and the HOI-motion injection, which enables complex human-object interactions by overcoming challenges in object trajectory conditioning and inter-occlusion management. Additionally, we introduce the HOI-region reweighting loss, a training objective that enhances the learning of object details. Extensive experiments demonstrate that our proposed system outperforms existing methods in preserving object appearance and shape awareness, while simultaneously maintaining consistency in human appearance and motion. Project page: https://cangcz.github.io/Anchor-Crafter/