Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new objects into a scene in a controllable manner. Fortunately, recent advancements in text-to-video (T2V) diffusion models pave the way for text-guided video inpainting. However, directly adapting T2V models for inpainting remains limited in unifying completion and insertion tasks, lacks input controllability, and struggles with long videos, thereby restricting their applicability and flexibility. To address these challenges, we propose MTV-Inpaint, a unified multi-task video inpainting framework capable of handling both traditional scene completion and novel object insertion tasks. To unify these distinct tasks, we design a dual-branch spatial attention mechanism in the T2V diffusion U-Net, enabling seamless integration of scene completion and object insertion within a single framework. In addition to textual guidance, MTV-Inpaint supports multimodal control by integrating various image inpainting models through our proposed image-to-video (I2V) inpainting mode. Additionally, we propose a two-stage pipeline that combines keyframe inpainting with in-between frame propagation, enabling MTV-Inpaint to effectively handle long videos with hundreds of frames. Extensive experiments demonstrate that MTV-Inpaint achieves state-of-the-art performance in both scene completion and object insertion tasks. Furthermore, it demonstrates versatility in derived applications such as multi-modal inpainting, object editing, removal, image object brush, and the ability to handle long videos. Project page: https://mtv-inpaint.github.io/.
Being hit by a ball is usually not a pleasant experience. While a ball may not be fatal, other objects can be. To protect themselves, many organisms, from humans to insects, have developed neuronal mechanisms to signal approaching objects such as predators and obstacles. The study of these neuronal circuits is still ongoing, both experimentally and theoretically. Many computational proposals rely on temporal contrast integration, as it encodes how the visual angle of an approaching object changes with time. However, mechanisms based on contrast integration are severely limited when the observer is also moving, as it is difficult to distinguish the background-induced temporal contrast from that of an approaching object. Here, I present results of a new mechanism for signaling object approaches, based on modern content-addressable (auto-associative) memories. Auto-associative memories were first proposed by Hopfield in 1982, and are a class of simple neuronal networks which transform incomplete or noisy input patterns to complete and noise-free output patterns. The memory holds different sizes of a generic pattern template that is efficient for segregating an approaching object from irrelevant background motion. Therefore, the model's output correlates directly with angular size. Generally, the new mechanism performs on a par with previously published models. The overall performance was systematically evaluated based on the network's responses to artificial and real-world video footage.
Learning robotic manipulation skills from vision is a promising approach for developing robotics applications that can generalize broadly to real-world scenarios. As such, many approaches to enable this vision have been explored with fruitful results. Particularly, object-centric representation methods have been shown to provide better inductive biases for skill learning, leading to improved performance and generalization. Nonetheless, we show that object-centric methods can struggle to learn simple manipulation skills in multi-object environments. Thus, we propose DOCIR, an object-centric framework that introduces a disentangled representation for objects of interest, obstacles, and robot embodiment. We show that this approach leads to state-of-the-art performance for learning pick and place skills from visual inputs in multi-object environments and generalizes at test time to changing objects of interest and distractors in the scene. Furthermore, we show its efficacy both in simulation and zero-shot transfer to the real world.
We address key limitations in existing datasets and models for task-oriented hand-object interaction video generation, a critical approach of generating video demonstrations for robotic imitation learning. Current datasets, such as Ego4D, often suffer from inconsistent view perspectives and misaligned interactions, leading to reduced video quality and limiting their applicability for precise imitation learning tasks. Towards this end, we introduce TASTE-Rob -- a pioneering large-scale dataset of 100,856 ego-centric hand-object interaction videos. Each video is meticulously aligned with language instructions and recorded from a consistent camera viewpoint to ensure interaction clarity. By fine-tuning a Video Diffusion Model (VDM) on TASTE-Rob, we achieve realistic object interactions, though we observed occasional inconsistencies in hand grasping postures. To enhance realism, we introduce a three-stage pose-refinement pipeline that improves hand posture accuracy in generated videos. Our curated dataset, coupled with the specialized pose-refinement framework, provides notable performance gains in generating high-quality, task-oriented hand-object interaction videos, resulting in achieving superior generalizable robotic manipulation. The TASTE-Rob dataset is publicly available to foster further advancements in the field, TASTE-Rob dataset and source code will be made publicly available on our website https://taste-rob.github.io.
Object-Centric Process Mining (OCPM) enables business process analysis from multiple perspectives. For example, an educational path can be examined from the viewpoints of students, teachers, and groups. This analysis depends on Object-Centric Event Data (OCED), which captures relationships between events and object types, representing different perspectives. Unlike traditional process mining techniques, extracting OCED minimizes the need for repeated log extractions when shifting the analytical focus. However, recording these complex relationships increases the complexity of the log extraction process. To address this challenge, this paper proposes a methodology for extracting OCED based on PM\inst{2}, a well-established process mining framework. Our approach introduces a structured framework that guides data analysts and engineers in extracting OCED for process analysis. We validate this framework by applying it in a real-world educational setting, demonstrating its effectiveness in extracting an Object-Centric Event Log (OCEL), which serves as the standard format for recording OCED, from a learning management system and an administrative grading system.
Object tracking is an essential task for autonomous systems. With the advancement of 3D sensors, these systems can better perceive their surroundings using effective 3D Extended Object Tracking (EOT) methods. Based on the observation that common road users are symmetrical on the right and left sides in the traveling direction, we focus on the side view profile of the object. In order to leverage of the development in 2D EOT and balance the number of parameters of a shape model in the tracking algorithms, we propose a method for 3D extended object tracking (EOT) by describing the side view profile of the object with B-spline curves and forming an extrusion to obtain a 3D extent. The use of B-spline curves exploits their flexible representation power by allowing the control points to move freely. The algorithm is developed into an Extended Kalman Filter (EKF). For a through evaluation of this method, we use simulated traffic scenario of different vehicle models and realworld open dataset containing both radar and lidar data.
LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal information remains an open problem. In this paper, we propose a novel Semantic-Supervised Spatial-Temporal Fusion (ST-Fusion) method, which introduces a novel fusion module to relieve the spatial misalignment caused by the object motion over time and a feature-level semantic supervision to sufficiently unlock the capacity of the proposed fusion module. Specifically, the ST-Fusion consists of a Spatial Aggregation (SA) module and a Temporal Merging (TM) module. The SA module employs a convolutional layer with progressively expanding receptive fields to aggregate the object features from the local regions to alleviate the spatial misalignment, the TM module dynamically extracts object features from the preceding frames based on the attention mechanism for a comprehensive sequential presentation. Besides, in the semantic supervision, we propose a Semantic Injection method to enrich the sparse LiDAR data via injecting the point-wise semantic labels, using it for training a teacher model and providing a reconstruction target at the feature level supervised by the proposed object-aware loss. Extensive experiments on various LiDAR-based detectors demonstrate the effectiveness and universality of our proposal, yielding an improvement of approximately +2.8% in NDS based on the nuScenes benchmark.
In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not only an arbitrary number of text-referred targets but also their interacting counterparts in the query from the video, making it more flexible and practical in real scenarios for comprehensive understanding. In order to facilitate exploration of OmniSTVG, we introduce BOSTVG, a large-scale benchmark dedicated to OmniSTVG. Specifically, our BOSTVG consists of 10,018 videos with 10.2M frames and covers a wide selection of 287 classes from diverse scenarios. Each sequence in BOSTVG, paired with a free-form textual query, encompasses a varying number of targets ranging from 1 to 10. To ensure high quality, each video is manually annotated with meticulous inspection and refinement. To our best knowledge, BOSTVG is to date the first and the largest benchmark for OmniSTVG. To encourage future research, we introduce a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results. By releasing BOSTVG, we hope to go beyond classic STVG by locating every object appearing in the query for more comprehensive understanding, opening up a new direction for STVG. Our benchmark, model, and results will be released at https://github.com/JellyYao3000/OmniSTVG.
Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations, achieving precision and efficiency in 3D static scenes, it lacks the ability to handle dynamic 4D fields as CLIP, designed for static image-text tasks, cannot capture temporal dynamics in videos. Real-world environments are inherently dynamic, with object semantics evolving over time. Building a precise 4D language field necessitates obtaining pixel-aligned, object-wise video features, which current vision models struggle to achieve. To address these challenges, we propose 4D LangSplat, which learns 4D language fields to handle time-agnostic or time-sensitive open-vocabulary queries in dynamic scenes efficiently. 4D LangSplat bypasses learning the language field from vision features and instead learns directly from text generated from object-wise video captions via Multimodal Large Language Models (MLLMs). Specifically, we propose a multimodal object-wise video prompting method, consisting of visual and text prompts that guide MLLMs to generate detailed, temporally consistent, high-quality captions for objects throughout a video. These captions are encoded using a Large Language Model into high-quality sentence embeddings, which then serve as pixel-aligned, object-specific feature supervision, facilitating open-vocabulary text queries through shared embedding spaces. Recognizing that objects in 4D scenes exhibit smooth transitions across states, we further propose a status deformable network to model these continuous changes over time effectively. Our results across multiple benchmarks demonstrate that 4D LangSplat attains precise and efficient results for both time-sensitive and time-agnostic open-vocabulary queries.
Recent developments in generative diffusion models have turned many dreams into realities. For video object insertion, existing methods typically require additional information, such as a reference video or a 3D asset of the object, to generate the synthetic motion. However, inserting an object from a single reference photo into a target background video remains an uncharted area due to the lack of unseen motion information. We propose DreamInsert, which achieves Image-to-Video Object Insertion in a training-free manner for the first time. By incorporating the trajectory of the object into consideration, DreamInsert can predict the unseen object movement, fuse it harmoniously with the background video, and generate the desired video seamlessly. More significantly, DreamInsert is both simple and effective, achieving zero-shot insertion without end-to-end training or additional fine-tuning on well-designed image-video data pairs. We demonstrated the effectiveness of DreamInsert through a variety of experiments. Leveraging this capability, we present the first results for Image-to-Video object insertion in a training-free manner, paving exciting new directions for future content creation and synthesis. The code will be released soon.
While the quality of novel-view images has improved dramatically with 3D Gaussian Splatting, extracting specific objects from scenes remains challenging. Isolating individual 3D Gaussian primitives for each object and handling occlusions in scenes remain far from being solved. We propose a novel object extraction method based on two key principles: (1) being object-centric by pruning irrelevant primitives; and (2) leveraging generative inpainting to compensate for missing observations caused by occlusions. For pruning, we analyze the local structure of primitives using K-nearest neighbors, and retain only relevant ones. For inpainting, we employ an off-the-shelf diffusion-based inpainter combined with occlusion reasoning, utilizing the 3D representation of the entire scene. Our findings highlight the crucial synergy between pruning and inpainting, both of which significantly enhance extraction performance. We evaluate our method on a standard real-world dataset and introduce a synthetic dataset for quantitative analysis. Our approach outperforms the state-of-the-art, demonstrating its effectiveness in object extraction from complex scenes.
Multi-object images are prevalent in various real-world scenarios, including augmented reality, advertisement design, and medical imaging. Efficient and precise editing of these images is critical for these applications. With the advent of Stable Diffusion (SD), high-quality image generation and editing have entered a new era. However, existing methods often struggle to consider each object both individually and part of the whole image editing, both of which are crucial for ensuring consistent quantity perception, resulting in suboptimal perceptual performance. To address these challenges, we propose MoEdit, an auxiliary-free multi-object image editing framework. MoEdit facilitates high-quality multi-object image editing in terms of style transfer, object reinvention, and background regeneration, while ensuring consistent quantity perception between inputs and outputs, even with a large number of objects. To achieve this, we introduce the Feature Compensation (FeCom) module, which ensures the distinction and separability of each object attribute by minimizing the in-between interlacing. Additionally, we present the Quantity Attention (QTTN) module, which perceives and preserves quantity consistency by effective control in editing, without relying on auxiliary tools. By leveraging the SD model, MoEdit enables customized preservation and modification of specific concepts in inputs with high quality. Experimental results demonstrate that our MoEdit achieves State-Of-The-Art (SOTA) performance in multi-object image editing. Data and codes will be available at https://github.com/Tear-kitty/MoEdit.
Unsupervised 3D object detection serves as an important solution for offline 3D object annotation. However, due to the data sparsity and limited views, the clustering-based label fitting in unsupervised object detection often generates low-quality pseudo-labels. Multi-agent collaborative dataset, which involves the sharing of complementary observations among agents, holds the potential to break through this bottleneck. In this paper, we introduce a novel unsupervised method that learns to Detect Objects from Multi-Agent LiDAR scans, termed DOtA, without using labels from external. DOtA first uses the internally shared ego-pose and ego-shape of collaborative agents to initialize the detector, leveraging the generalization performance of neural networks to infer preliminary labels. Subsequently,DOtA uses the complementary observations between agents to perform multi-scale encoding on preliminary labels, then decodes high-quality and low-quality labels. These labels are further used as prompts to guide a correct feature learning process, thereby enhancing the performance of the unsupervised object detection task. Extensive experiments on the V2V4Real and OPV2V datasets show that our DOtA outperforms state-of-the-art unsupervised 3D object detection methods. Additionally, we also validate the effectiveness of the DOtA labels under various collaborative perception frameworks.The code is available at https://github.com/xmuqimingxia/DOtA.
Object-centric learning is fundamental to human vision and crucial for models requiring complex reasoning. Traditional approaches rely on slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO have shown emergent object understanding. However, DINO representations primarily capture global scene features, often confounding individual object attributes. We investigate the effectiveness of DINO representations and slot-based methods for multi-object instance retrieval. Our findings reveal that DINO representations excel at capturing global object attributes such as object shape and size, but struggle with object-level details like colour, whereas slot-based representations struggle at both global and object-level understanding. To address this, we propose a method that combines global and local features by augmenting DINO representations with object-centric latent vectors from a Variational Autoencoder trained on segmented image patches that are extracted from the DINO features. This approach improves multi-object instance retrieval performance, bridging the gap between global scene understanding and fine-grained object representation without requiring full model retraining.
With the rapid advancement of large language models (LLMs) and vision-language models (VLMs), significant progress has been made in developing open-vocabulary robotic manipulation systems. However, many existing approaches overlook the importance of object dynamics, limiting their applicability to more complex, dynamic tasks. In this work, we introduce KUDA, an open-vocabulary manipulation system that integrates dynamics learning and visual prompting through keypoints, leveraging both VLMs and learning-based neural dynamics models. Our key insight is that a keypoint-based target specification is simultaneously interpretable by VLMs and can be efficiently translated into cost functions for model-based planning. Given language instructions and visual observations, KUDA first assigns keypoints to the RGB image and queries the VLM to generate target specifications. These abstract keypoint-based representations are then converted into cost functions, which are optimized using a learned dynamics model to produce robotic trajectories. We evaluate KUDA on a range of manipulation tasks, including free-form language instructions across diverse object categories, multi-object interactions, and deformable or granular objects, demonstrating the effectiveness of our framework. The project page is available at http://kuda-dynamics.github.io.
We seek to extract a temporally consistent 6D pose trajectory of a manipulated object from an Internet instructional video. This is a challenging set-up for current 6D pose estimation methods due to uncontrolled capturing conditions, subtle but dynamic object motions, and the fact that the exact mesh of the manipulated object is not known. To address these challenges, we present the following contributions. First, we develop a new method that estimates the 6D pose of any object in the input image without prior knowledge of the object itself. The method proceeds by (i) retrieving a CAD model similar to the depicted object from a large-scale model database, (ii) 6D aligning the retrieved CAD model with the input image, and (iii) grounding the absolute scale of the object with respect to the scene. Second, we extract smooth 6D object trajectories from Internet videos by carefully tracking the detected objects across video frames. The extracted object trajectories are then retargeted via trajectory optimization into the configuration space of a robotic manipulator. Third, we thoroughly evaluate and ablate our 6D pose estimation method on YCB-V and HOPE-Video datasets as well as a new dataset of instructional videos manually annotated with approximate 6D object trajectories. We demonstrate significant improvements over existing state-of-the-art RGB 6D pose estimation methods. Finally, we show that the 6D object motion estimated from Internet videos can be transferred to a 7-axis robotic manipulator both in a virtual simulator as well as in a real world set-up. We also successfully apply our method to egocentric videos taken from the EPIC-KITCHENS dataset, demonstrating potential for Embodied AI applications.
Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectiveness is limited. This is mainly because most existing crowd counting datasets on which the methods are trained are based on passive cameras, restricting their ability to fully sense the environment. Recently, embodied navigation methods have shown significant potential in precise object detection in interactive scenes. These methods incorporate active camera settings, holding promise in addressing the fundamental issues in crowd counting. However, most existing methods are designed for indoor navigation, showing unknown performance in analyzing complex object distribution in large scale scenes, such as crowds. Besides, most existing embodied navigation datasets are indoor scenes with limited scale and object quantity, preventing them from being introduced into dense crowd analysis. Based on this, a novel task, Embodied Crowd Counting (ECC), is proposed. We first build up an interactive simulator, Embodied Crowd Counting Dataset (ECCD), which enables large scale scenes and large object quantity. A prior probability distribution that approximates realistic crowd distribution is introduced to generate crowds. Then, a zero-shot navigation method (ZECC) is proposed. This method contains a MLLM driven coarse-to-fine navigation mechanism, enabling active Z-axis exploration, and a normal-line-based crowd distribution analysis method for fine counting. Experimental results against baselines show that the proposed method achieves the best trade-off between counting accuracy and navigation cost.
Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes rather than isolated tasks. Leveraging a pre-trained diffusion prior along with a progressive training pipeline comprising initial paired sample optimization and subsequent large-scale unpaired refinement via CycleFlow, OmniPaint achieves precise foreground elimination and seamless object insertion while faithfully preserving scene geometry and intrinsic properties. Furthermore, our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination, establishing a new benchmark for high-fidelity image editing. Project page: https://yeates.github.io/OmniPaint-Page/
We present GASPACHO: a method for generating photorealistic controllable renderings of human-object interactions. Given a set of multi-view RGB images of human-object interactions, our method reconstructs animatable templates of the human and object as separate sets of Gaussians simultaneously. Different from existing work, which focuses on human reconstruction and ignores objects as background, our method explicitly reconstructs both humans and objects, thereby allowing for controllable renderings of novel human object interactions in different poses from novel-camera viewpoints. During reconstruction, we constrain the Gaussians that generate rendered images to be a linear function of a set of canonical Gaussians. By simply changing the parameters of the linear deformation functions after training, our method can generate renderings of novel human-object interaction in novel poses from novel camera viewpoints. We learn the 3D Gaussian properties of the canonical Gaussians on the underlying 2D manifold of the canonical human and object templates. This in turns requires a canonical object template with a fixed UV unwrapping. To define such an object template, we use a feature based representation to track the object across the multi-view sequence. We further propose an occlusion aware photometric loss that allows for reconstructions under significant occlusions. Several experiments on two human-object datasets - BEHAVE and DNA-Rendering - demonstrate that our method allows for high-quality reconstruction of human and object templates under significant occlusion and the synthesis of controllable renderings of novel human-object interactions in novel human poses from novel camera views.
Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.