PyTorchKR Papers

최신 논문

총 1,880편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2412.03085

Mimir: Improving Video Diffusion Models for Precise Text Understanding

Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features from text encoders yet struggle with limited text comprehension. The recent success of large language models (LLMs) showcases the power of decoder-only transformers, which offers three clear benefits for text-to-video (T2V) generation, namely, precise text understanding resulting from the superior scalability, imagination beyond the input text enabled by next token prediction, and flexibility to prioritize user interests through instruction tuning. Nevertheless, the feature distribution gap emerging from the two different text modeling paradigms hinders the direct use of LLMs in established T2V models. This work addresses this challenge with Mimir, an end-to-end training framework featuring a carefully tailored token fuser to harmonize the outputs from text encoders and LLMs. Such a design allows the T2V model to fully leverage learned video priors while capitalizing on the text-related capability of LLMs. Extensive quantitative and qualitative results demonstrate the effectiveness of Mimir in generating high-quality videos with excellent text comprehension, especially when processing short captions and managing shifting motions. Project page: https://lucaria-academy.github.io/Mimir/

arXiv:2412.03552

Imagine360: Immersive 360 Video Generation from Perspective Anchor

$360^\circ$ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more user-friendly and personalized content creation in $360^\circ$ video format, we seek to lift standard perspective videos into $360^\circ$ equirectangular videos. To this end, we introduce Imagine360, the first perspective-to-$360^\circ$ video generation framework that creates high-quality $360^\circ$ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited $360^\circ$ video data with several key designs. 1) Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for $360^\circ$ video generation, with motion module and spatial LoRA layers fine-tuned on extended web $360^\circ$ videos. 2) Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. 3) To handle diverse perspective video inputs, we propose elevation-aware designs that adapt to varying video masking due to changing elevations across frames. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence among state-of-the-art $360^\circ$ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive $360^\circ$ video creation.

arXiv:2412.03520

Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention

Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial, temporal, and view dimensions. However, these approaches often struggle to maintain consistency across dimensions, particularly when handling fast-moving objects that appear at different times and viewpoints. In this paper, we present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the spatial, temporal, and viewpoint dimensions. We also propose a lightweight controller tailored for CogDriving, i.e., Micro-Controller, which uses only 1.1% of the parameters of the standard ControlNet, enabling precise control over Bird's-Eye-View layouts. To enhance the generation of object instances crucial for autonomous driving, we propose a re-weighted learning objective, dynamically adjusting the learning weights for object instances during training. CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos. The project can be found at https://luhannan.github.io/CogDrivingPage/.

arXiv:2412.03572

Navigation World Models

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and navigation actions. To capture complex environment dynamics, NWM employs a Conditional Diffusion Transformer (CDiT), trained on a diverse collection of egocentric videos of both human and robotic agents, and scaled up to 1 billion parameters. In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desired goal. Unlike supervised navigation policies with fixed behavior, NWM can dynamically incorporate constraints during planning. Experiments demonstrate its effectiveness in planning trajectories from scratch or by ranking trajectories sampled from an external policy. Furthermore, NWM leverages its learned visual priors to imagine trajectories in unfamiliar environments from a single input image, making it a flexible and powerful tool for next-generation navigation systems.

arXiv:2412.00131공식 코드 · Papers with Code

Open-Sora Plan: Open-Source Large Video Generation Model

We introduce Open-Sora Plan, an open-source project that aims to contribute a large generation model for generating desired high-resolution videos with long durations based on various user inputs. Our project comprises multiple components for the entire video generation process, including a Wavelet-Flow Variational Autoencoder, a Joint Image-Video Skiparse Denoiser, and various condition controllers. Moreover, many assistant strategies for efficient training and inference are designed, and a multi-dimensional data curation pipeline is proposed for obtaining desired high-quality data. Benefiting from efficient thoughts, our Open-Sora Plan achieves impressive video generation results in both qualitative and quantitative evaluations. We hope our careful design and practical experience can inspire the video generation research community. All our codes and model weights are publicly available at \url{https://github.com/PKU-YuanGroup/Open-Sora-Plan}.

arXiv:2412.00719

Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation

Talking head video generation aims to generate a realistic talking head video that preserves the person's identity from a source image and the motion from a driving video. Despite the promising progress made in the field, it remains a challenging and critical problem to generate videos with accurate poses and fine-grained facial details simultaneously. Essentially, facial motion is often highly complex to model precisely, and the one-shot source face image cannot provide sufficient appearance guidance during generation due to dynamic pose changes. To tackle the problem, we propose to jointly learn motion and appearance codebooks and perform multi-scale codebook compensation to effectively refine both the facial motion conditions and appearance features for talking face image decoding. Specifically, the designed multi-scale motion and appearance codebooks are learned simultaneously in a unified framework to store representative global facial motion flow and appearance patterns. Then, we present a novel multi-scale motion and appearance compensation module, which utilizes a transformer-based codebook retrieval strategy to query complementary information from the two codebooks for joint motion and appearance compensation. The entire process produces motion flows of greater flexibility and appearance features with fewer distortions across different scales, resulting in a high-quality talking head video generation framework. Extensive experiments on various benchmarks validate the effectiveness of our approach and demonstrate superior generation results from both qualitative and quantitative perspectives when compared to state-of-the-art competitors.

arXiv:2412.01821

World-consistent Video Diffusion with Explicit 3D Modeling

Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly generating 3D-consistent content. To address this, we propose World-consistent Video Diffusion (WVD), a novel framework that incorporates explicit 3D supervision using XYZ images, which encode global 3D coordinates for each image pixel. More specifically, we train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. This approach supports multi-task adaptability via a flexible inpainting strategy. For example, WVD can estimate XYZ frames from ground-truth RGB or generate novel RGB frames using XYZ projections along a specified camera trajectory. In doing so, WVD unifies tasks like single-image-to-3D generation, multi-view stereo, and camera-controlled video generation. Our approach demonstrates competitive performance across multiple benchmarks, providing a scalable solution for 3D-consistent video and image generation with a single pretrained model.

arXiv:2412.01522

InfinityDrive: Breaking Time Limits in Driving World Models

Autonomous driving systems struggle with complex scenarios due to limited access to diverse, extensive, and out-of-distribution driving data which are critical for safe navigation. World models offer a promising solution to this challenge; however, current driving world models are constrained by short time windows and limited scenario diversity. To bridge this gap, we introduce InfinityDrive, the first driving world model with exceptional generalization capabilities, delivering state-of-the-art performance in high fidelity, consistency, and diversity with minute-scale video generation. InfinityDrive introduces an efficient spatio-temporal co-modeling module paired with an extended temporal training strategy, enabling high-resolution (576$\times$1024) video generation with consistent spatial and temporal coherence. By incorporating memory injection and retention mechanisms alongside an adaptive memory curve loss to minimize cumulative errors, achieving consistent video generation lasting over 1500 frames (more than 2 minutes). Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving. Our project homepage: https://metadrivescape.github.io/papers_project/InfinityDrive/page.html

arXiv:2412.01429

CPA: Camera-pose-awareness Diffusion Transformer for Video Generation

Despite the significant advancements made by Diffusion Transformer (DiT)-based methods in video generation, there remains a notable gap with controllable camera pose perspectives. Existing works such as OpenSora do NOT adhere precisely to anticipated trajectories and physical interactions, thereby limiting the flexibility in downstream applications. To alleviate this issue, we introduce CPA, a unified camera-pose-awareness text-to-video generation approach that elaborates the camera movement and integrates the textual, visual, and spatial conditions. Specifically, we deploy the Sparse Motion Encoding (SME) module to transform camera pose information into a spatial-temporal embedding and activate the Temporal Attention Injection (TAI) module to inject motion patches into each ST-DiT block. Our plug-in architecture accommodates the original DiT parameters, facilitating diverse types of camera poses and flexible object movement. Extensive qualitative and quantitative experiments demonstrate that our method outperforms LDM-based methods for long video generation while achieving optimal performance in trajectory consistency and object consistency.

arXiv:2412.01343

MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

Existing pretrained text-to-video (T2V) models have demonstrated impressive abilities in generating realistic videos with basic motion or camera movement. However, these models exhibit significant limitations when generating intricate, human-centric motions. Current efforts primarily focus on fine-tuning models on a small set of videos containing a specific motion. They often fail to effectively decouple motion and the appearance in the limited reference videos, thereby weakening the modeling capability of motion patterns. To this end, we propose MoTrans, a customized motion transfer method enabling video generation of similar motion in new context. Specifically, we introduce a multimodal large language model (MLLM)-based recaptioner to expand the initial prompt to focus more on appearance and an appearance injection module to adapt appearance prior from video frames to the motion modeling process. These complementary multimodal representations from recaptioned prompt and video frames promote the modeling of appearance and facilitate the decoupling of appearance and motion. In addition, we devise a motion-specific embedding for further enhancing the modeling of the specific motion. Experimental results demonstrate that our method effectively learns specific motion pattern from singular or multiple reference videos, performing favorably against existing methods in customized video generation.

arXiv:2412.02700

Motion Prompting: Controlling Video Generation with Motion Trajectories

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal compositions. To this end, we train a video generation model conditioned on spatio-temporally sparse or dense motion trajectories. In contrast to prior motion conditioning work, this flexible representation can encode any number of trajectories, object-specific or global scene motion, and temporally sparse motion; due to its flexibility we refer to this conditioning as motion prompts. While users may directly specify sparse trajectories, we also show how to translate high-level user requests into detailed, semi-dense motion prompts, a process we term motion prompt expansion. We demonstrate the versatility of our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing. Our results showcase emergent behaviors, such as realistic physics, suggesting the potential of motion prompts for probing video models and interacting with future generative world models. Finally, we evaluate quantitatively, conduct a human study, and demonstrate strong performance. Video results are available on our webpage: https://motion-prompting.github.io/

arXiv:2412.00526

Human Action CLIPs: Detecting AI-generated Human Motion

AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its malicious applications, we describe an effective and robust technique for distinguishing real from AI-generated human motion using multi-modal semantic embeddings. Our method is robust to the types of laundering that typically confound more low- to mid-level approaches, including resolution and compression attacks. This method is evaluated against DeepAction, a custom-built, open-sourced dataset of video clips with human actions generated by seven text-to-video AI models and matching real footage. The dataset is available under an academic license at https://www.huggingface.co/datasets/faridlab/deepaction_v1.

arXiv:2412.00115

OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

Recent advancements in visual generation technologies have markedly increased the scale and availability of video datasets, which are crucial for training effective video generation models. However, a significant lack of high-quality, human-centric video datasets presents a challenge to progress in this field. To bridge this gap, we introduce OpenHumanVid, a large-scale and high-quality human-centric video dataset characterized by precise and detailed captions that encompass both human appearance and motion states, along with supplementary human motion conditions, including skeleton sequences and speech audio. To validate the efficacy of this dataset and the associated training strategies, we propose an extension of existing classical diffusion transformer architectures and conduct further pretraining of our models on the proposed dataset. Our findings yield two critical insights: First, the incorporation of a large-scale, high-quality dataset substantially enhances evaluation metrics for generated human videos while preserving performance in general video generation tasks. Second, the effective alignment of text with human appearance, human motion, and facial motion is essential for producing high-quality video outputs. Based on these insights and corresponding methodologies, the straightforward extended network trained on the proposed dataset demonstrates an obvious improvement in the generation of human-centric videos. Project page https://fudan-generative-vision.github.io/OpenHumanVid

arXiv:2412.01064

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

With the rapid advancement of diffusion-based generative models, portrait image animation has achieved remarkable results. However, it still faces challenges in temporally consistent video generation and fast sampling due to its iterative sampling nature. This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. We shift the generative modeling from the pixel-based latent space to a learned motion latent space, enabling efficient design of temporally consistent motion. To achieve this, we introduce a transformer-based vector field predictor with a simple yet effective frame-wise conditioning mechanism. Additionally, our method supports speech-driven emotion enhancement, enabling a natural incorporation of expressive motions. Extensive experiments demonstrate that our method outperforms state-of-the-art audio-driven talking portrait methods in terms of visual quality, motion fidelity, and efficiency.

arXiv:2412.00773

DIVD: Deblurring with Improved Video Diffusion Model

Video deblurring presents a considerable challenge owing to the complexity of blur, which frequently results from a combination of camera shakes, and object motions. In the field of video deblurring, many previous works have primarily concentrated on distortion-based metrics, such as PSNR. However, this approach often results in a weak correlation with human perception and yields reconstructions that lack realism. Diffusion models and video diffusion models have respectively excelled in the fields of image and video generation, particularly achieving remarkable results in terms of image authenticity and realistic perception. However, due to the computational complexity and challenges inherent in adapting diffusion models, there is still uncertainty regarding the potential of video diffusion models in video deblurring tasks. To explore the viability of video diffusion models in the task of video deblurring, we introduce a diffusion model specifically for this purpose. In this field, leveraging highly correlated information between adjacent frames and addressing the challenge of temporal misalignment are crucial research directions. To tackle these challenges, many improvements based on the video diffusion model are introduced in this work. As a result, our model outperforms existing models and achieves state-of-the-art results on a range of perceptual metrics. Our model preserves a significant amount of detail in the images while maintaining competitive distortion metrics. Furthermore, to the best of our knowledge, this is the first time the diffusion model has been applied in video deblurring to overcome the limitations mentioned above.

arXiv:2412.00596공식 코드 · Papers with Code

PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding of physical realism and deficiency in temporal modeling. Existing solutions are either data-driven or require extra model inputs, but cannot be generalizable to out-of-distribution domains. In this paper, we present PhyT2V, a new data-independent T2V technique that expands the current T2V model's capability of video generation to out-of-distribution domains, by enabling chain-of-thought and step-back reasoning in T2V prompting. Our experiments show that PhyT2V improves existing T2V models' adherence to real-world physical rules by 2.3x, and achieves 35% improvement compared to T2V prompt enhancers. The source codes are available at: https://github.com/pittisl/PhyT2V.

arXiv:2412.00547공식 코드 · Papers with Code

Motion Dreamer: Realizing Physically Coherent Video Generation through Scene-Aware Motion Reasoning

Recent numerous video generation models, also known as world models, have demonstrated the ability to generate plausible real-world videos. However, many studies have shown that these models often produce motion results lacking logical or physical coherence. In this paper, we revisit video generation models and find that single-stage approaches struggle to produce high-quality results while maintaining coherent motion reasoning. To address this issue, we propose \textbf{Motion Dreamer}, a two-stage video generation framework. In Stage I, the model generates an intermediate motion representation-such as a segmentation map or depth map-based on the input image and motion conditions, focusing solely on the motion itself. In Stage II, the model uses this intermediate motion representation as a condition to generate a high-detail video. By decoupling motion reasoning from high-fidelity video synthesis, our approach allows for more accurate and physically plausible motion generation. We validate the effectiveness of our approach on the Physion dataset and in autonomous driving scenarios. For example, given a single push, our model can synthesize the sequential toppling of a set of dominoes. Similarly, by varying the movements of ego-cars, our model can produce different effects on other vehicles. Our work opens new avenues in creating models that can reason about physical interactions in a more coherent and realistic manner. Our webpage is available: https://envision-research.github.io/MotionDreamer/.

arXiv:2412.01316

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain scenario diversity over long durations presents significant challenges. To address this, we propose a Segmented Cross-Attention (SCA) strategy, which splits hidden states into segments along the temporal dimension, allowing each segment to cross-attend to a corresponding sub-caption. SCA requires no additional parameters, enabling seamless incorporation into current DiT-based architectures. To facilitate high-quality long video generation, we build the LongTake-HD dataset, consisting of 261k content-rich videos with scenario coherence, annotated with an overall video caption and five progressive sub-captions. Experiments show that our Presto achieves 78.5% on the VBench Semantic Score and 100% on the Dynamic Degree, outperforming existing state-of-the-art video generation methods. This demonstrates that our proposed Presto significantly enhances content richness, maintains long-range coherence, and captures intricate textual details. More details are displayed on our project page: https://presto-video.github.io/.

arXiv:2412.02684

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative approaches for controllable animation, though avoiding explicit 3D modeling, suffer from viewpoint inconsistencies in extreme poses and computational inefficiencies. In this paper, we address these challenges by leveraging the power of generative models to produce detailed multi-view canonical pose images, which help resolve ambiguities in animatable human reconstruction. We then propose a robust method for 3D reconstruction of inconsistent images, enabling real-time rendering during inference. Specifically, we adapt a transformer-based video generation model to generate multi-view canonical pose images and normal maps, pretraining on a large-scale video dataset to improve generalization. To handle view inconsistencies, we recast the reconstruction problem as a 4D task and introduce an efficient 3D modeling approach using 4D Gaussian Splatting. Experiments demonstrate that our method achieves photorealistic, real-time animation of 3D human avatars from in-the-wild images, showcasing its effectiveness and generalization capability.

arXiv:2412.02617cs.LG

Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback

대형 텍스트-투-비디오(text-to-video) 생성 모델은 문장과 장면의 정합성을 어느 정도 구현했지만, 객체가 서로 부딪히고, 떨어지고, 끌리며 상호작용하는 장면에서는 여전히 비현실적인 움직임과 물리 법칙 위반을 자주 드러냅니다. 이러한 한계를 해결하기 위해 저자들은 생성 결과를 외부 피드백으로 정렬하는 관점에서 문제를 다시 바라보고, 특히 동적 객체 상호작용의 품질을 높이기 위한 학습 신호가 무엇이어야 하는지에 초점을 맞춥니다. 먼저 디노이징 확산 확률 모델(Denoising Diffusion Probabilistic Model, DDPM) 기반의 비디오 생성 과정을 마르코프 결정 과정(Markov Decision Process, MDP)으로 해석하여, 역확산의 각 단계가 정책(policy)의 행동 선택에 해당한다는 점을 보이고, 최종 보상만 주어지는 강화학습(reinforcement learning, RL) 문제로 자연스럽게 연결합니다. 이 관점에서 기존의 여러 오프라인 RL 파인튜닝 기법들은 서로 다른 알고리즘처럼 보이더라도 사실상 하나의 확률적 목적 함수에서 유도될 수 있으며, 따라서 알고리즘 자체의 우열보다 보상 설계와 학습 데이터의 성질이 더 중요하다는 결론에 도달합니다. 다시 말해, 어떤 방법을 쓰느냐보다 어떤 피드백이 객체 상호작용의 실제 오류를 더 정확히 포착하느냐가 성능을 좌우한다는 것입니다. 이 연구의 핵심 제안은 인간 피드백의 확장성 한계를 고려해, 장면을 사람처럼 해석할 수 있는 비전-언어 모델(vision-language model, VLM)을 이용해 객체 동역학에 특화된 이진 AI 피드백을 생성하는 데 있습니다. 저자들은 이 피드백이 단순한 미적 선호가 아니라, 움직임의 타당성, 접촉의 자연스러움, 낙하나 충돌 같은 물리적 사건의 현실성을 직접적으로 반영해야 한다고 보고, 이를 통해 생성 모델이 더 정밀하게 스스로를 개선하도록 유도합니다. 또한 이 접근은 policy projection, 기대최대화(expectation-maximization, EM), 브래들리-테리(Bradley-Terry) 가정 등 서로 다른 오프라인 최적화 관점들을 하나의 통합된 확률적 추론 틀 안에서 이해하게 해 주어, 방법론의 해석 가능성을 크게 높입니다. 실험적으로는 VLM에서 얻은 이진 AI 피드백이 동적 객체 상호작용 장면의 품질을 가장 크게 끌어올렸고, AI 평가와 인간 평가, 그리고 품질 지표 모두에서 일관된 향상을 보였습니다. 특히 여러 객체가 동시에 얽히는 복잡한 상호작용이나 물체가 떨어지는 장면처럼 물리적으로 어려운 상황에서 개선 폭이 두드러졌다는 점은, 이 피드백이 실제 동역학 오류를 잘 감지한다는 사실을 뒷받침합니다. 결국 이 논문은 텍스트-투-비디오 생성에서 동작의 사실성과 물리적 일관성을 높이기 위해서는, 더 복잡한 알고리즘보다도 장면의 동역학을 이해하는 피드백 신호를 어떻게 설계하느냐가 결정적이라는 점을 설득력 있게 보여줍니다.