Existing VLMs can track in-the-wild 2D video objects while current generative models provide powerful visual priors for synthesizing novel views for the highly under-constrained 2D-to-3D object lifting. Building upon this exciting progress, we present DreamScene4D, the first approach that can generate three-dimensional dynamic scenes of multiple objects from monocular in-the-wild videos with large object motion across occlusions and novel viewpoints. Our key insight is to design a "decompose-then-recompose" scheme to factorize both the whole video scene and each object's 3D motion. We first decompose the video scene by using open-vocabulary mask trackers and an adapted image diffusion model to segment, track, and amodally complete the objects and background in the video. Each object track is mapped to a set of 3D Gaussians that deform and move in space and time. We also factorize the observed motion into multiple components to handle fast motion. The camera motion can be inferred by re-rendering the background to match the video frames. For the object motion, we first model the object-centric deformation of the objects by leveraging rendering losses and multi-view generative priors in an object-centric frame, then optimize object-centric to world-frame transformations by comparing the rendered outputs against the perceived pixel and optical flow. Finally, we recompose the background and objects and optimize for relative object scales using monocular depth prediction guidance. We show extensive results on the challenging DAVIS, Kubric, and self-captured videos, detail some limitations, and provide future directions. Besides 4D scene generation, our results show that DreamScene4D enables accurate 2D point motion tracking by projecting the inferred 3D trajectories to 2D, while never explicitly trained to do so.
相關內容
With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a single target to inter-target relationships, covering holistic aspects of spatial and attribute understanding. The overall pipeline incorporates powerful VLMs via carefully designed prompts to initialize the annotations efficiently and further involve humans' correction in the loop to ensure the annotations are natural, correct, and comprehensive. Built upon existing 3D scanning data, the resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks. We evaluate representative baselines on our benchmarks, analyze their capabilities in different aspects, and showcase the key problems to be addressed in the future. Furthermore, we use this high-quality dataset to train state-of-the-art 3D visual grounding and LLMs and obtain remarkable performance improvement both on existing benchmarks and in-the-wild evaluation. Codes, datasets, and benchmarks will be available at //github.com/OpenRobotLab/EmbodiedScan.
We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame. This enables learning disentangled appearance and pose features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image architecture of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open).
Generating realistic audio for human interactions is important for many applications, such as creating sound effects for films or virtual reality games. Existing approaches implicitly assume total correspondence between the video and audio during training, yet many sounds happen off-screen and have weak to no correspondence with the visuals -- resulting in uncontrolled ambient sounds or hallucinations at test time. We propose a novel ambient-aware audio generation model, AV-LDM. We devise a novel audio-conditioning mechanism to learn to disentangle foreground action sounds from the ambient background sounds in in-the-wild training videos. Given a novel silent video, our model uses retrieval-augmented generation to create audio that matches the visual content both semantically and temporally. We train and evaluate our model on two in-the-wild egocentric video datasets Ego4D and EPIC-KITCHENS. Our model outperforms an array of existing methods, allows controllable generation of the ambient sound, and even shows promise for generalizing to computer graphics game clips. Overall, our work is the first to focus video-to-audio generation faithfully on the observed visual content despite training from uncurated clips with natural background sounds.
We propose LASER, a neuro-symbolic approach to learn semantic video representations that capture rich spatial and temporal properties in video data by leveraging high-level logic specifications. In particular, we formulate the problem in terms of alignment between raw videos and spatio-temporal logic specifications. The alignment algorithm leverages a differentiable symbolic reasoner and a combination of contrastive, temporal, and semantics losses. It effectively and efficiently trains low-level perception models to extract a fine-grained video representation in the form of a spatio-temporal scene graph that conforms to the desired high-level specification. To practically reduce the manual effort of obtaining ground truth labels, we derive logic specifications from captions by employing a large language model with a generic prompting template. In doing so, we explore a novel methodology that weakly supervises the learning of spatio-temporal scene graphs with widely accessible video-caption data. We evaluate our method on three datasets with rich spatial and temporal specifications: 20BN-Something-Something, MUGEN, and OpenPVSG. We demonstrate that our method learns better fine-grained video semantics than existing baselines.
The effectiveness and efficiency of modeling complex spectral-spatial relations are both crucial for Hyperspectral image (HSI) classification. Most existing methods based on CNNs and transformers still suffer from heavy computational burdens and have room for improvement in capturing the global-local spectral-spatial feature representation. To this end, we propose a novel lightweight parallel design called lightweight dual-stream Mamba-convolution network (DualMamba) for HSI classification. Specifically, a parallel lightweight Mamba and CNN block are first developed to extract global and local spectral-spatial features. First, the cross-attention spectral-spatial Mamba module is proposed to leverage the global modeling of Mamba at linear complexity. Within this module, dynamic positional embedding is designed to enhance the spatial location information of visual sequences. The lightweight spectral/spatial Mamba blocks comprise an efficient scanning strategy and a lightweight Mamba design to efficiently extract global spectral-spatial features. And the cross-attention spectral-spatial fusion is designed to learn cross-correlation and fuse spectral-spatial features. Second, the lightweight spectral-spatial residual convolution module is proposed with lightweight spectral and spatial branches to extract local spectral-spatial features through residual learning. Finally, the adaptive global-local fusion is proposed to dynamically combine global Mamba features and local convolution features for a global-local spectral-spatial representation. Compared with state-of-the-art HSI classification methods, experimental results demonstrate that DualMamba achieves significant classification accuracy on three public HSI datasets and a superior reduction in model parameters and floating point operations (FLOPs).
Existing video captioning benchmarks and models lack coherent representations of causal-temporal narrative, which is sequences of events linked through cause and effect, unfolding over time and driven by characters or agents. This lack of narrative restricts models' ability to generate text descriptions that capture the causal and temporal dynamics inherent in video content. To address this gap, we propose NarrativeBridge, an approach comprising of: (1) a novel Causal-Temporal Narrative (CTN) captions benchmark generated using a large language model and few-shot prompting, explicitly encoding cause-effect temporal relationships in video descriptions, evaluated automatically to ensure caption quality and relevance; and (2) a dedicated Cause-Effect Network (CEN) architecture with separate encoders for capturing cause and effect dynamics independently, enabling effective learning and generation of captions with causal-temporal narrative. Extensive experiments demonstrate that CEN is more accurate in articulating the causal and temporal aspects of video content than the second best model (GIT): 17.88 and 17.44 CIDEr on the MSVD and MSR-VTT datasets, respectively. The proposed framework understands and generates nuanced text descriptions with intricate causal-temporal narrative structures present in videos, addressing a critical limitation in video captioning. For project details, visit //narrativebridge.github.io/.
Autonomous Driving (AD) systems critically depend on visual perception for real-time object detection and multiple object tracking (MOT) to ensure safe driving. However, high latency in these visual perception components can lead to significant safety risks, such as vehicle collisions. While previous research has extensively explored latency attacks within the digital realm, translating these methods effectively to the physical world presents challenges. For instance, existing attacks rely on perturbations that are unrealistic or impractical for AD, such as adversarial perturbations affecting areas like the sky, or requiring large patches that obscure most of a camera's view, thus making them impossible to be conducted effectively in the real world. In this paper, we introduce SlowPerception, the first physical-world latency attack against AD perception, via generating projector-based universal perturbations. SlowPerception strategically creates numerous phantom objects on various surfaces in the environment, significantly increasing the computational load of Non-Maximum Suppression (NMS) and MOT, thereby inducing substantial latency. Our SlowPerception achieves second-level latency in physical-world settings, with an average latency of 2.5 seconds across different AD perception systems, scenarios, and hardware configurations. This performance significantly outperforms existing state-of-the-art latency attacks. Additionally, we conduct AD system-level impact assessments, such as vehicle collisions, using industry-grade AD systems with production-grade AD simulators with a 97% average rate. We hope that our analyses can inspire further research in this critical domain, enhancing the robustness of AD systems against emerging vulnerabilities.
We consider a problem in Multi-Task Learning (MTL) where multiple linear models are jointly trained on a collection of datasets ("tasks"). A key novelty of our framework is that it allows the sparsity pattern of regression coefficients and the values of non-zero coefficients to differ across tasks while still leveraging partially shared structure. Our methods encourage models to share information across tasks through separately encouraging 1) coefficient supports, and/or 2) nonzero coefficient values to be similar. This allows models to borrow strength during variable selection even when non-zero coefficient values differ across tasks. We propose a novel mixed-integer programming formulation for our estimator. We develop custom scalable algorithms based on block coordinate descent and combinatorial local search to obtain high-quality (approximate) solutions for our estimator. Additionally, we propose a novel exact optimization algorithm to obtain globally optimal solutions. We investigate the theoretical properties of our estimators. We formally show how our estimators leverage the shared support information across tasks to achieve better variable selection performance. We evaluate the performance of our methods in simulations and two biomedical applications. Our proposed approaches appear to outperform other sparse MTL methods in variable selection and prediction accuracy. We provide the sMTL package on CRAN.
Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial examples using hard labels obtained from the target machine learning model. This is typically realized by optimizing perturbation directions, guided by decision boundaries identified through query-intensive exact search, significantly limiting the attack success rate. This paper introduces a novel approach using the Approximation Decision Boundary (ADB) to efficiently and accurately compare perturbation directions without precisely determining decision boundaries. The effectiveness of our ADB approach (ADBA) hinges on promptly identifying suitable ADB, ensuring reliable differentiation of all perturbation directions. For this purpose, we analyze the probability distribution of decision boundaries, confirming that using the distribution's median value as ADB can effectively distinguish different perturbation directions, giving rise to the development of the ADBA-md algorithm. ADBA-md only requires four queries on average to differentiate any pair of perturbation directions, which is highly query-efficient. Extensive experiments on six well-known image classifiers clearly demonstrate the superiority of ADBA and ADBA-md over multiple state-of-the-art black-box attacks.
This survey presents an overview of methods for learning from video (LfV) in the context of reinforcement learning (RL) and robotics. We focus on methods capable of scaling to large internet video datasets and, in the process, extracting foundational knowledge about the world's dynamics and physical human behaviour. Such methods hold great promise for developing general-purpose robots. We open with an overview of fundamental concepts relevant to the LfV-for-robotics setting. This includes a discussion of the exciting benefits LfV methods can offer (e.g., improved generalization beyond the available robot data) and commentary on key LfV challenges (e.g., missing information in video and LfV distribution shifts). Our literature review begins with an analysis of video foundation model techniques that can extract knowledge from large, heterogeneous video datasets. Next, we review methods that specifically leverage video data for robot learning. Here, we categorise work according to which RL knowledge modality (KM) benefits from the use of video data. We additionally highlight techniques for mitigating LfV challenges, including reviewing action representations that address missing action labels in video. Finally, we examine LfV datasets and benchmarks, before concluding with a discussion of challenges and opportunities in LfV. Here, we advocate for scalable foundation model approaches that can leverage the full range of internet video data, and that target the learning of the most promising RL KMs: the policy and dynamics model. Overall, we hope this survey will serve as a comprehensive reference for the emerging field of LfV, catalysing further research in the area and facilitating progress towards the development of general-purpose robots.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191