Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular motion cues or incorporate fine-tuning to inject certain motion patterns, resulting in limited flexibility and generalization. In this work, we propose MotionClone, a training-free framework that enables motion cloning from reference videos to versatile motion-controlled video generation, including text-to-video and image-to-video. Based on the observation that the dominant components in temporal-attention maps drive motion synthesis, while the rest mainly capture noisy or very subtle motions, MotionClone utilizes sparse temporal attention weights as motion representations for motion guidance, facilitating diverse motion transfer across varying scenarios. Meanwhile, MotionClone allows for the direct extraction of motion representation through a single denoising step, bypassing the cumbersome inversion processes and thus promoting both efficiency and flexibility. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency.
相關內容
We propose the new task 'open-world video instance segmentation and captioning'. It requires to detect, segment, track and describe with rich captions never before seen objects. This challenging task can be addressed by developing "abstractors" which connect a vision model and a language foundation model. Concretely, we connect a multi-scale visual feature extractor and a large language model (LLM) by developing an object abstractor and an object-to-text abstractor. The object abstractor, consisting of a prompt encoder and transformer blocks, introduces spatially-diverse open-world object queries to discover never before seen objects in videos. An inter-query contrastive loss further encourages the diversity of object queries. The object-to-text abstractor is augmented with masked cross-attention and acts as a bridge between the object queries and a frozen LLM to generate rich and descriptive object-centric captions for each detected object. Our generalized approach surpasses the baseline that jointly addresses the tasks of open-world video instance segmentation and dense video object captioning by 13% on never before seen objects, and by 10% on object-centric captions.
Visual artifacts are often introduced into streamed video content, due to prevailing conditions during content production and delivery. Since these can degrade the quality of the user's experience, it is important to automatically and accurately detect them in order to enable effective quality measurement and enhancement. Existing detection methods often focus on a single type of artifact and/or determine the presence of an artifact through thresholding objective quality indices. Such approaches have been reported to offer inconsistent prediction performance and are also impractical for real-world applications where multiple artifacts co-exist and interact. In this paper, we propose a Multiple Visual Artifact Detector, MVAD, for video streaming which, for the first time, is able to detect multiple artifacts using a single framework that is not reliant on video quality assessment models. Our approach employs a new Artifact-aware Dynamic Feature Extractor (ADFE) to obtain artifact-relevant spatial features within each frame for multiple artifact types. The extracted features are further processed by a Recurrent Memory Vision Transformer (RMViT) module, which captures both short-term and long-term temporal information within the input video. The proposed network architecture is optimized in an end-to-end manner based on a new, large and diverse training database that is generated by simulating the video streaming pipeline and based on Adversarial Data Augmentation. This model has been evaluated on two video artifact databases, Maxwell and BVI-Artifact, and achieves consistent and improved prediction results for ten target visual artifacts when compared to seven existing single and multiple artifact detectors. The source code and training database will be available at //chenfeng-bristol.github.io/MVAD/.
Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods remain prohibitively expensive and challenging to deploy on mobile devices. In this study, we introduce a series of optimizations that render mobile video editing feasible. Building upon the existing image editing model, we first optimize its architecture and incorporate a lightweight autoencoder. Subsequently, we extend classifier-free guidance distillation to multiple modalities, resulting in a threefold on-device speedup. Finally, we reduce the number of sampling steps to one by introducing a novel adversarial distillation scheme which preserves the controllability of the editing process. Collectively, these optimizations enable video editing at 12 frames per second on mobile devices, while maintaining high quality. Our results are available at //qualcomm-ai-research.github.io/mobile-video-editing/
Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However, these models often struggle to represent high-frequency details due to the limited number of Gaussians. While the densification strategy used in per-scene 3D Gaussian splatting (3D-GS) optimization can be adapted to the feed-forward models, it may not be ideally suited for generalized scenarios. In this paper, we propose Generative Densification, an efficient and generalizable method to densify Gaussians generated by feed-forward models. Unlike the 3D-GS densification strategy, which iteratively splits and clones raw Gaussian parameters, our method up-samples feature representations from the feed-forward models and generates their corresponding fine Gaussians in a single forward pass, leveraging the embedded prior knowledge for enhanced generalization. Experimental results on both object-level and scene-level reconstruction tasks demonstrate that our method outperforms state-of-the-art approaches with comparable or smaller model sizes, achieving notable improvements in representing fine details.
Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limiting their practical applicability. We introduce MotionFlow, a novel framework designed for motion transfer in video diffusion models. Our method utilizes cross-attention maps to accurately capture and manipulate spatial and temporal dynamics, enabling seamless motion transfers across various contexts. Our approach does not require training and works on test-time by leveraging the inherent capabilities of pre-trained video diffusion models. In contrast to traditional approaches, which struggle with comprehensive scene changes while maintaining consistent motion, MotionFlow successfully handles such complex transformations through its attention-based mechanism. Our qualitative and quantitative experiments demonstrate that MotionFlow significantly outperforms existing models in both fidelity and versatility even during drastic scene alterations.
We propose 4Real-Video, a novel framework for generating 4D videos, organized as a grid of video frames with both time and viewpoint axes. In this grid, each row contains frames sharing the same timestep, while each column contains frames from the same viewpoint. We propose a novel two-stream architecture. One stream performs viewpoint updates on columns, and the other stream performs temporal updates on rows. After each diffusion transformer layer, a synchronization layer exchanges information between the two token streams. We propose two implementations of the synchronization layer, using either hard or soft synchronization. This feedforward architecture improves upon previous work in three ways: higher inference speed, enhanced visual quality (measured by FVD, CLIP, and VideoScore), and improved temporal and viewpoint consistency (measured by VideoScore and Dust3R-Confidence).
This work presents Switti, a scale-wise transformer for text-to-image generation. Starting from existing next-scale prediction AR models, we first explore them for T2I generation and propose architectural modifications to improve their convergence and overall performance. We then argue that scale-wise transformers do not require causality and propose a non-causal counterpart facilitating ~11% faster sampling and lower memory usage while also achieving slightly better generation quality. Furthermore, we reveal that classifier-free guidance at high-resolution scales is often unnecessary and can even degrade performance. By disabling guidance at these scales, we achieve an additional sampling acceleration of ~20% and improve the generation of fine-grained details. Extensive human preference studies and automated evaluations show that Switti outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7 times faster.
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing natural, audio-aligned expressions in generated talking videos remain significant challenges. To address these challenges, we propose Memory-guided EMOtion-aware diffusion (MEMO), an end-to-end audio-driven portrait animation approach to generate identity-consistent and expressive talking videos. Our approach is built around two key modules: (1) a memory-guided temporal module, which enhances long-term identity consistency and motion smoothness by developing memory states to store information from a longer past context to guide temporal modeling via linear attention; and (2) an emotion-aware audio module, which replaces traditional cross attention with multi-modal attention to enhance audio-video interaction, while detecting emotions from audio to refine facial expressions via emotion adaptive layer norm. Extensive quantitative and qualitative results demonstrate that MEMO generates more realistic talking videos across diverse image and audio types, outperforming state-of-the-art methods in overall quality, audio-lip synchronization, identity consistency, and expression-emotion alignment.
This paper introduces a novel clothed human model that can be learned from multiview RGB videos, with a particular emphasis on recovering physically accurate body and cloth movements. Our method, Position Based Dynamic Gaussians (PBDyG), realizes ``movement-dependent'' cloth deformation via physical simulation, rather than merely relying on ``pose-dependent'' rigid transformations. We model the clothed human holistically but with two distinct physical entities in contact: clothing modeled as 3D Gaussians, which are attached to a skinned SMPL body that follows the movement of the person in the input videos. The articulation of the SMPL body also drives physically-based simulation of the clothes' Gaussians to transform the avatar to novel poses. In order to run position based dynamics simulation, physical properties including mass and material stiffness are estimated from the RGB videos through Dynamic 3D Gaussian Splatting. Experiments demonstrate that our method not only accurately reproduces appearance but also enables the reconstruction of avatars wearing highly deformable garments, such as skirts or coats, which have been challenging to reconstruct using existing methods.
Recovering metric depth from a single image remains a fundamental challenge in computer vision, requiring both scene understanding and accurate scaling. While deep learning has advanced monocular depth estimation, current models often struggle with unfamiliar scenes and layouts, particularly in zero-shot scenarios and when predicting scale-ergodic metric depth. We present MetricGold, a novel approach that harnesses generative diffusion model's rich priors to improve metric depth estimation. Building upon recent advances in MariGold, DDVM and Depth Anything V2 respectively, our method combines latent diffusion, log-scaled metric depth representation, and synthetic data training. MetricGold achieves efficient training on a single RTX 3090 within two days using photo-realistic synthetic data from HyperSIM, VirtualKitti, and TartanAir. Our experiments demonstrate robust generalization across diverse datasets, producing sharper and higher quality metric depth estimates compared to existing approaches.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191