Deep neural networks (DNNs) often exhibit biases toward certain categories during object recognition, even under balanced training data conditions. The intrinsic mechanisms underlying these biases remain unclear. Inspired by the human visual system, which decouples object manifolds through hierarchical processing to achieve object recognition, we propose a geometric analysis framework linking the geometric complexity of class-specific perceptual manifolds in DNNs to model bias. Our findings reveal that differences in geometric complexity can lead to varying recognition capabilities across categories, introducing biases. To support this analysis, we present the Perceptual-Manifold-Geometry library, designed for calculating the geometric properties of perceptual manifolds.
Transformer has attracted increasing interest in STVG, owing to its end-to-end pipeline and promising result. Existing Transformer-based STVG approaches often leverage a set of object queries, which are initialized simply using zeros and then gradually learn target position information via iterative interactions with multimodal features, for spatial and temporal localization. Despite simplicity, these zero object queries, due to lacking target-specific cues, are hard to learn discriminative target information from interactions with multimodal features in complicated scenarios (\e.g., with distractors or occlusion), resulting in degradation. Addressing this, we introduce a novel Target-Aware Transformer for STVG (TA-STVG), which seeks to adaptively generate object queries via exploring target-specific cues from the given video-text pair, for improving STVG. The key lies in two simple yet effective modules, comprising text-guided temporal sampling (TTS) and attribute-aware spatial activation (ASA), working in a cascade. The former focuses on selecting target-relevant temporal cues from a video utilizing holistic text information, while the latter aims at further exploiting the fine-grained visual attribute information of the object from previous target-aware temporal cues, which is applied for object query initialization. Compared to existing methods leveraging zero-initialized queries, object queries in our TA-STVG, directly generated from a given video-text pair, naturally carry target-specific cues, making them adaptive and better interact with multimodal features for learning more discriminative information to improve STVG. In our experiments on three benchmarks, TA-STVG achieves state-of-the-art performance and significantly outperforms the baseline, validating its efficacy.
This work focuses on model-free zero-shot 6D object pose estimation for robotics applications. While existing methods can estimate the precise 6D pose of objects, they heavily rely on curated CAD models or reference images, the preparation of which is a time-consuming and labor-intensive process. Moreover, in real-world scenarios, 3D models or reference images may not be available in advance and instant robot reaction is desired. In this work, we propose a novel framework named HIPPo, which eliminates the need for curated CAD models and reference images by harnessing image-to-3D priors from Diffusion Models, enabling model-free zero-shot 6D pose estimation. Specifically, we construct HIPPo Dreamer, a rapid image-to-mesh model built on a multiview Diffusion Model and a 3D reconstruction foundation model. Our HIPPo Dreamer can generate a 3D mesh of any unseen objects from a single glance in just a few seconds. Then, as more observations are acquired, we propose to continuously refine the diffusion prior mesh model by joint optimization of object geometry and appearance. This is achieved by a measurement-guided scheme that gradually replaces the plausible diffusion priors with more reliable online observations. Consequently, HIPPo can instantly estimate and track the 6D pose of a novel object and maintain a complete mesh for immediate robotic applications. Thorough experiments on various benchmarks show that HIPPo outperforms state-of-the-art methods in 6D object pose estimation when prior reference images are limited.
The use of control barrier functions under uncertain pose information of multiple small servicing agents is analyzed for a satellite servicing application. The application consists of modular servicing agents deployed towards a tumbling space object from a mothership. Relative position and orientation of each agent is obtained via fusion of relative range and inertial measurement sensors. The control barrier functions are utilized to avoid collisions with other agents for the application of simultaneously relocating servicing agents on a tumbling body. A differential collision detection and avoidance framework using the polytopic hull of the tumbling space object is utilized to safely guide the agents away from the tumbling object.
Motion capture systems are a widespread tool in research to record ground-truth poses of objects. Commercial systems use reflective markers attached to the object and then triangulate pose of the object from multiple camera views. Consequently, the object must be visible to multiple cameras which makes such multi-view motion capture systems unsuited for deployments in narrow, confined spaces (e.g. ballast tanks of ships). In this technical report we describe a monocular event-camera motion capture system which overcomes this limitation and is ideally suited for narrow spaces. Instead of passive markers it relies on active, blinking LED markers such that each marker can be uniquely identified from the blinking frequency. The markers are placed at known locations on the tracking object. We then solve the PnP (perspective-n-points) problem to obtain the position and orientation of the object. The developed system has millimeter accuracy, millisecond latency and we demonstrate that its state estimate can be used to fly a small, agile quadrotor.
Efficient and accurate object detection is an important topic in the development of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased significantly. The project aims to integrate a modern technique for object detection with the aim of achieving high accuracy with real-time performance. The reliance on other computer vision algorithms in many object identification systems, which results in poor and ineffective performance, is a significant obstacle. In this research, we solve the end-to-end object detection problem entirely using deep learning techniques. The network is trained using the most difficult publicly available dataset, which is used for an annual item detection challenge. Applications that need object detection can benefit the system's quick and precise finding.
In this work, we present CineMaster, a novel framework for 3D-aware and controllable text-to-video generation. Our goal is to empower users with comparable controllability as professional film directors: precise placement of objects within the scene, flexible manipulation of both objects and camera in 3D space, and intuitive layout control over the rendered frames. To achieve this, CineMaster operates in two stages. In the first stage, we design an interactive workflow that allows users to intuitively construct 3D-aware conditional signals by positioning object bounding boxes and defining camera movements within the 3D space. In the second stage, these control signals--comprising rendered depth maps, camera trajectories and object class labels--serve as the guidance for a text-to-video diffusion model, ensuring to generate the user-intended video content. Furthermore, to overcome the scarcity of in-the-wild datasets with 3D object motion and camera pose annotations, we carefully establish an automated data annotation pipeline that extracts 3D bounding boxes and camera trajectories from large-scale video data. Extensive qualitative and quantitative experiments demonstrate that CineMaster significantly outperforms existing methods and implements prominent 3D-aware text-to-video generation. Project page: https://cinemaster-dev.github.io/.
We present ATOP (Articulate That Object Part), a novel method based on motion personalization to articulate a 3D object with respect to a part and its motion as prescribed in a text prompt. Specifically, the text input allows us to tap into the power of modern-day video diffusion to generate plausible motion samples for the right object category and part. In turn, the input 3D object provides image prompting to personalize the generated video to that very object we wish to articulate. Our method starts with a few-shot finetuning for category-specific motion generation, a key first step to compensate for the lack of articulation awareness by current video diffusion models. For this, we finetune a pre-trained multi-view image generation model for controllable multi-view video generation, using a small collection of video samples obtained for the target object category. This is followed by motion video personalization that is realized by multi-view rendered images of the target 3D object. At last, we transfer the personalized video motion to the target 3D object via differentiable rendering to optimize part motion parameters by a score distillation sampling loss. We show that our method is capable of generating realistic motion videos and predict 3D motion parameters in a more accurate and generalizable way, compared to prior works.
Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as non-maximum suppression (NMS), often produce many repetitive predictions or missed detections in dense scenarios, which is a common problem faced by NMS-based algorithms. Through the end-to-end DETR (DEtection TRansformer), as a type of detector that can incorporate the post-processing de-duplication capability of NMS, etc., into the network, we found that homogeneous queries in the query-based detector lead to a reduction in the de-duplication capability of the network and the learning efficiency of the encoder, resulting in duplicate prediction and missed detection problems. To solve this problem, we propose learnable differentiated encoding to de-homogenize the queries, and at the same time, queries can communicate with each other via differentiated encoding information, replacing the previous self-attention among the queries. In addition, we used joint loss on the output of the encoder that considered both location and confidence prediction to give a higher-quality initialization for queries. Without cumbersome decoder stacking and guaranteeing accuracy, our proposed end-to-end detection framework was more concise and reduced the number of parameters by about 8% compared to deformable DETR. Our method achieved excellent results on the challenging CrowdHuman dataset with 93.6% average precision (AP), 39.2% MR-2, and 84.3% JI. The performance overperformed previous SOTA methods, such as Iter-E2EDet (Progressive End-to-End Object Detection) and MIP (One proposal, Multiple predictions). In addition, our method is more robust in various scenarios with different densities.
As the demand for privacy in visual data management grows, safeguarding sensitive information has become a critical challenge. This paper addresses the need for privacy-preserving solutions in large-scale visual data processing by leveraging federated learning. Although there have been developments in this field, previous research has mainly focused on integrating object detection with either anonymization or federated learning. However, these pairs often fail to address complex privacy concerns. On the one hand, object detection with anonymization alone can be vulnerable to reverse techniques. On the other hand, federated learning may not provide sufficient privacy guarantees. Therefore, we propose a new approach that combines object detection, federated learning and anonymization. Combining these three components aims to offer a robust privacy protection strategy by addressing different vulnerabilities in visual data. Our solution is evaluated against traditional centralized models, showing that while there is a slight trade-off in accuracy, the privacy benefits are substantial, making it well-suited for privacy sensitive applications.
Predicting future scene representations is a crucial task for enabling robots to understand and interact with the environment. However, most existing methods rely on videos and simulations with precise action annotations, limiting their ability to leverage the large amount of available unlabeled video data. To address this challenge, we propose PlaySlot, an object-centric video prediction model that infers object representations and latent actions from unlabeled video sequences. It then uses these representations to forecast future object states and video frames. PlaySlot allows the generation of multiple possible futures conditioned on latent actions, which can be inferred from video dynamics, provided by a user, or generated by a learned action policy, thus enabling versatile and interpretable world modeling. Our results show that PlaySlot outperforms both stochastic and object-centric baselines for video prediction across different environments. Furthermore, we show that our inferred latent actions can be used to learn robot behaviors sample-efficiently from unlabeled video demonstrations. Videos and code are available on https://play-slot.github.io/PlaySlot/.
Recent image-to-video generation methods have demonstrated success in enabling control over one or two visual elements, such as camera motion or object motion. However, these methods are unable to offer control over multiple visual elements due to limitations in data and network efficacy. In this paper, we introduce VidCRAFT3, a novel framework for precise image-to-video generation that enables control over camera motion, object motion, and lighting direction simultaneously. VidCRAFT3 integrates three core components: Image2Cloud generates 3D point cloud from a reference image; ObjMotionNet encodes sparse object trajectories using multi-scale optical flow features; and Spatial Triple-Attention Transformer incorporates lighting direction embeddings via parallel cross-attention modules. Additionally, we introduce the VideoLightingDirection dataset, providing synthetic yet realistic video clips with accurate per-frame lighting direction annotations, effectively mitigating the lack of annotated real-world datasets. We further adopt a three-stage training strategy, ensuring robust learning even without joint multi-element annotations. Extensive experiments show that VidCRAFT3 produces high-quality video content, outperforming state-of-the-art methods in control granularity and visual coherence. Code and data will be publicly available.
In the field of computer vision, 6D object detection and pose estimation are critical for applications such as robotics, augmented reality, and autonomous driving. Traditional methods often struggle with achieving high accuracy in both object detection and precise pose estimation simultaneously. This study proposes an improved 6D object detection and pose estimation pipeline based on the existing 6D-VNet framework, enhanced by integrating a Hybrid Task Cascade (HTC) and a High-Resolution Network (HRNet) backbone. By leveraging the strengths of HTC's multi-stage refinement process and HRNet's ability to maintain high-resolution representations, our approach significantly improves detection accuracy and pose estimation precision. Furthermore, we introduce advanced post-processing techniques and a novel model integration strategy that collectively contribute to superior performance on public and private benchmarks. Our method demonstrates substantial improvements over state-of-the-art models, making it a valuable contribution to the domain of 6D object detection and pose estimation.
Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a fundamental reason behind this limitation: VLMs features space exhibits significant semantic entanglement, where features of one class contain substantial information about other unrelated classes, a phenomenon we term mutual feature information (MFI). This entanglement becomes evident during class-specific queries, as unrelated objects are activated alongside the queried class. To address this limitation, we propose DCLIP, a framework that disentangles CLIP features using two complementary objectives: a novel MFI Loss that orthogonalizes the text (class) features to reduce inter-class similarity, and the Asymmetric Loss (ASL) that aligns image features with the disentangled text features. Our experiment demonstrates that DCLIP reduces inter-class feature similarity by 30\% compared to CLIP, leading to significant performance gains on multi-label recognition (MLR) and zero-shot semantic segmentation (ZS3). In MLR, DCLIP outperforms SOTA approaches on VOC2007 and COCO-14 while using 75\% fewer parameters, and surpasses SOTA ZS3 methods by 3.4 mIoU on VOC2012 and 2.8 mIoU on COCO-17. These results establish feature disentanglement as a critical factor for effective multi-object perception in vision-language models.
We present a validation dataset of newly-collected kitchen-based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to recognise recipes, ingredients, nutrition, fine-grained actions, 3D perception, object motion, and gaze direction. The powerful long-context Gemini Pro only achieves 38.5% on this benchmark, showcasing its difficulty and highlighting shortcomings in current VLMs. We additionally assess action recognition, sound recognition, and long-term video-object segmentation on HD-EPIC. HD-EPIC is 41 hours of video in 9 kitchens with digital twins of 413 kitchen fixtures, capturing 69 recipes, 59K fine-grained actions, 51K audio events, 20K object movements and 37K object masks lifted to 3D. On average, we have 263 annotations per minute of our unscripted videos.
We present the first text-based image editing approach for object parts based on pre-trained diffusion models. Diffusion-based image editing approaches capitalized on the deep understanding of diffusion models of image semantics to perform a variety of edits. However, existing diffusion models lack sufficient understanding of many object parts, hindering fine-grained edits requested by users. To address this, we propose to expand the knowledge of pre-trained diffusion models to allow them to understand various object parts, enabling them to perform fine-grained edits. We achieve this by learning special textual tokens that correspond to different object parts through an efficient token optimization process. These tokens are optimized to produce reliable localization masks at each inference step to localize the editing region. Leveraging these masks, we design feature-blending and adaptive thresholding strategies to execute the edits seamlessly. To evaluate our approach, we establish a benchmark and an evaluation protocol for part editing. Experiments show that our approach outperforms existing editing methods on all metrics and is preferred by users 77-90% of the time in conducted user studies.
Recent state-of-the-art object segmentation mechanisms, such as the Segment Anything Model (SAM) and FastSAM, first encode the full image over several layers and then focus on generating the mask for one particular object or area. We present an off-grid Fovea-Like Input Patching (FLIP) approach, which selects image input and encodes it from the beginning in an object-focused manner. While doing so, it separates locational encoding from an object-centric perceptual code. FLIP is more data-efficient and yields improved segmentation performance when masking relatively small objects in high-resolution visual scenes. On standard benchmarks such as Hypersim, KITTI-360, and OpenImages, FLIP achieves Intersection over Union (IoU) scores that approach the performance of SAM with much less compute effort. It surpasses FastSAM in all IoU measurements. We also introduce an additional semi-natural but highly intuitive dataset where FLIP outperforms SAM and FastSAM overall and particularly on relatively small objects. Seeing that FLIP is an end-to-end object-centric segmentation approach, it has high potential particularly for applications that benefit from computationally efficient, spatially highly selective object tracking.
This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries through a relation-aware self-attention mechanism, which adaptively learns to balance different scales of relations (local, medium and global) across decoder layers. This progressive design enables the model to effectively capture evolving spatial dependencies throughout the detection pipeline. Extensive experiments on COCO 2017 dataset demonstrate that our method improves both convergence speed and detection accuracy compared to standard self-attention module. The proposed method achieves competitive results, reaching 52.3\% AP with 12 epochs and 52.5\% AP with 24 epochs using ResNet-50 backbone, and further improving to 58.0\% AP with Swin-L backbone. Furthermore, our analysis reveals an interesting pattern: the model naturally learns to prioritize local spatial relations in early decoder layers while gradually shifting attention to broader contexts in deeper layers, providing valuable insights for future research in object detection.
Unmanned aerial vehicles (UAVs) are widely used for object detection. However, the existing UAV-based object detection systems are subject to severe challenges, namely, their limited computation, energy and communication resources, which limits the achievable detection performance. To overcome these challenges, a UAV cognitive semantic communication system is proposed by exploiting a knowledge graph. Moreover, we design a multi-scale codec for semantic compression to reduce data transmission volume while guaranteeing detection performance. Considering the complexity and dynamicity of UAV communication scenarios, a signal-to-noise ratio (SNR) adaptive module with robust channel adaptation capability is introduced. Furthermore, an object detection scheme is proposed by exploiting the knowledge graph to overcome channel noise interference and compression distortion. Simulation results conducted on the practical aerial image dataset demonstrate that our proposed semantic communication system outperforms benchmark systems in terms of detection accuracy, communication robustness, and computation efficiency, especially in dealing with low bandwidth compression ratios and low SNR regimes.
Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretability and robustness. Through experiments on LIBERO-spatial pick-and-place tasks, we analyze the encoding of symbolic states across different layers of OpenVLA's Llama backbone. Our probing results show consistently high accuracies (> 0.90) for both object and action states across most layers, though contrary to our hypotheses, we did not observe the expected pattern of object states being encoded earlier than action states. We demonstrate an integrated DIARC-OpenVLA system that leverages these symbolic representations for real-time state monitoring, laying the foundation for more interpretable and reliable robotic manipulation.