Multiple object tracking is a critical task in autonomous driving. Existing works primarily focus on the heuristic design of neural networks to obtain high accuracy. As tracking accuracy improves, however, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency. In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for low real-time latency while maintaining relatively high accuracy. Another challenge for object tracking is the unreliability of a single sensor, therefore, we propose a multi-modal framework to improve the robustness. Experiments demonstrate that our algorithm can run on edge devices within lower latency constraints, thus greatly reducing the computational requirements for multi-modal object tracking while keeping lower latency.
Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose. While gradient-based optimization in a NeRF framework updates the initial pose, this paper highlights that scale-depth ambiguity in monocular object reconstruction causes failures when the initial pose deviates moderately from the true pose. Consequently, existing methods often depend on a third-party 3D object to provide an initial object pose, leading to increased complexity and generalization issues. To address these challenges, we present SUP-NeRF, a Streamlined Unification of object Pose estimation and NeRF-based object reconstruction. SUP-NeRF decouples the object's dimension estimation and pose refinement to resolve the scale-depth ambiguity, and introduces a camera-invariant projected-box representation that generalizes cross different domains. While using a dedicated pose estimator that smoothly integrates into an object-centric NeRF, SUP-NeRF is free from external 3D detectors. SUP-NeRF achieves state-of-the-art results in both reconstruction and pose estimation tasks on the nuScenes dataset. Furthermore, SUP-NeRF exhibits exceptional cross-dataset generalization on the KITTI and Waymo datasets, surpassing prior methods with up to 50\% reduction in rotation and translation error.
In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We identify and address two key challenges: the unsatisfactory outcomes of direct text-to-3D methods in HOI, largely due to the lack of paired text-interaction data, and the inherent difficulties in simultaneously generating multiple concepts with complex spatial relationships. To effectively address these issues, we present InterFusion, a two-stage framework specifically designed for HOI generation. InterFusion involves human pose estimations derived from text as geometric priors, which simplifies the text-to-3D conversion process and introduces additional constraints for accurate object generation. At the first stage, InterFusion extracts 3D human poses from a synthesized image dataset depicting a wide range of interactions, subsequently mapping these poses to interaction descriptions. The second stage of InterFusion capitalizes on the latest developments in text-to-3D generation, enabling the production of realistic and high-quality 3D HOI scenes. This is achieved through a local-global optimization process, where the generation of human body and object is optimized separately, and jointly refined with a global optimization of the entire scene, ensuring a seamless and contextually coherent integration. Our experimental results affirm that InterFusion significantly outperforms existing state-of-the-art methods in 3D HOI generation.
Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computational burden. To address the first challenge, we introduce ElysiumTrack-1M, a large-scale video dataset supported for three tasks: Single Object Tracking (SOT), Referring Single Object Tracking (RSOT), and Video Referring Expression Generation (Video-REG). ElysiumTrack-1M contains 1.27 million annotated video frames with corresponding object boxes and descriptions. Leveraging this dataset, we conduct training of MLLMs and propose a token-compression model T-Selector to tackle the second challenge. Our proposed approach, Elysium: Exploring Object-level Perception in Videos via MLLM, is an end-to-end trainable MLLM that attempts to conduct object-level tasks in videos without requiring any additional plug-in or expert models. All codes and datasets are available at https://github.com/Hon-Wong/Elysium.
Three-dimensional object detection is one of the key tasks in autonomous driving. To reduce costs in practice, low-cost multi-view cameras for 3D object detection are proposed to replace the expansive LiDAR sensors. However, relying solely on cameras is difficult to achieve highly accurate and robust 3D object detection. An effective solution to this issue is combining multi-view cameras with the economical millimeter-wave radar sensor to achieve more reliable multi-modal 3D object detection. In this paper, we introduce RCBEVDet, a radar-camera fusion 3D object detection method in the bird's eye view (BEV). Specifically, we first design RadarBEVNet for radar BEV feature extraction. RadarBEVNet consists of a dual-stream radar backbone and a Radar Cross-Section (RCS) aware BEV encoder. In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders. The RCS-aware BEV encoder takes RCS as the object size prior to scattering the point feature in BEV. Besides, we present the Cross-Attention Multi-layer Fusion module to automatically align the multi-modal BEV feature from radar and camera with the deformable attention mechanism, and then fuse the feature with channel and spatial fusion layers. Experimental results show that RCBEVDet achieves new state-of-the-art radar-camera fusion results on nuScenes and view-of-delft (VoD) 3D object detection benchmarks. Furthermore, RCBEVDet achieves better 3D detection results than all real-time camera-only and radar-camera 3D object detectors with a faster inference speed at 21~28 FPS. The source code will be released at https://github.com/VDIGPKU/RCBEVDet.
We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in 3D is challenging due to heavy occlusion, viewpoint bias, camera distortion, and motion blur from the head movement. To this end, we designed the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks. Our analysis demonstrates the effectiveness of addressing distortion specific to egocentric cameras, adopting high-capacity transformers to learn complex hand-object interactions, and fusing predictions from different views. Our study further reveals challenging scenarios intractable with state-of-the-art methods, such as fast hand motion, object reconstruction from narrow egocentric views, and close contact between two hands and objects. Our efforts will enrich the community's knowledge foundation and facilitate future hand studies on egocentric hand-object interactions.
In medical and industrial domains, providing guidance for assembly processes can be critical to ensure efficiency and safety. Errors in assembly can lead to significant consequences such as extended surgery times and prolonged manufacturing or maintenance times in industry. Assembly scenarios can benefit from in-situ augmented reality visualization, i.e., augmentations in close proximity to the target object, to provide guidance, reduce assembly times, and minimize errors. In order to enable in-situ visualization, 6D pose estimation can be leveraged to identify the correct location for an augmentation. Existing 6D pose estimation techniques primarily focus on individual objects and static captures. However, assembly scenarios have various dynamics, including occlusion during assembly and dynamics in the appearance of assembly objects. Existing work focus either on object detection combined with state detection, or focus purely on the pose estimation. To address the challenges of 6D pose estimation in combination with assembly state detection, our approach ASDF builds upon the strengths of YOLOv8, a real-time capable object detection framework. We extend this framework, refine the object pose, and fuse pose knowledge with network-detected pose information. Utilizing our late fusion in our Pose2State module results in refined 6D pose estimation and assembly state detection. By combining both pose and state information, our Pose2State module predicts the final assembly state with precision. The evaluation of our ASDF dataset shows that our Pose2State module leads to an improved assembly state detection and that the improvement of the assembly state further leads to a more robust 6D pose estimation. Moreover, on the GBOT dataset, we outperform the pure deep learning-based network and even outperform the hybrid and pure tracking-based approaches.
With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, where crucial factors (e.g., data distribution, objective) that influence model learning are often changing. The dynamic and intricate nature of the open environment poses novel and formidable challenges to object detectors. Unfortunately, current research on object detectors in open environments lacks a comprehensive analysis of their distinctive characteristics, challenges, and corresponding solutions, which hinders their secure deployment in critical real-world scenarios. This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments. We initially identified limitations of key structural components within the existing detection pipeline and propose the open environment object detector challenge framework that includes four quadrants (i.e., out-of-domain, out-of-category, robust learning, and incremental learning) based on the dimensions of the data / target changes. For each quadrant of challenges in the proposed framework, we present a detailed description and systematic analysis of the overarching goals and core difficulties, systematically review the corresponding solutions, and benchmark their performance over multiple widely adopted datasets. In addition, we engage in a discussion of open problems and potential avenues for future research. This paper aims to provide a fresh, comprehensive, and systematic understanding of the challenges and solutions associated with open-environment object detectors, thus catalyzing the development of more solid applications in real-world scenarios. A project related to this survey can be found at https://github.com/LiangSiyuan21/OEOD_Survey.
Cross-modal feature extraction and integration have led to steady performance improvements in few-shot learning tasks due to generating richer features. However, existing multi-modal object detection (MM-OD) methods degrade when facing significant domain-shift and are sample insufficient. We hypothesize that rich text information could more effectively help the model to build a knowledge relationship between the vision instance and its language description and can help mitigate domain shift. Specifically, we study the Cross-Domain few-shot generalization of MM-OD (CDMM-FSOD) and propose a meta-learning based multi-modal few-shot object detection method that utilizes rich text semantic information as an auxiliary modality to achieve domain adaptation in the context of FSOD. Our proposed network contains (i) a multi-modal feature aggregation module that aligns the vision and language support feature embeddings and (ii) a rich text semantic rectify module that utilizes bidirectional text feature generation to reinforce multi-modal feature alignment and thus to enhance the model's language understanding capability. We evaluate our model on common standard cross-domain object detection datasets and demonstrate that our approach considerably outperforms existing FSOD methods.
In Multiple Object Tracking (MOT), tracking-by-detection methods have stood the test for a long time, which split the process into two parts according to the definition: object detection and association. They leverage robust single-frame detectors and treat object association as a post-processing step through hand-crafted heuristic algorithms and surrogate tasks. However, the nature of heuristic techniques prevents end-to-end exploitation of training data, leading to increasingly cumbersome and challenging manual modification while facing complicated or novel scenarios. In this paper, we regard this object association task as an End-to-End in-context ID prediction problem and propose a streamlined baseline called MOTIP. Specifically, we form the target embeddings into historical trajectory information while considering the corresponding IDs as in-context prompts, then directly predict the ID labels for the objects in the current frame. Thanks to this end-to-end process, MOTIP can learn tracking capabilities straight from training data, freeing itself from burdensome hand-crafted algorithms. Without bells and whistles, our method achieves impressive state-of-the-art performance in complex scenarios like DanceTrack and SportsMOT, and it performs competitively with other transformer-based methods on MOT17. We believe that MOTIP demonstrates remarkable potential and can serve as a starting point for future research. The code is available at https://github.com/MCG-NJU/MOTIP.
Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments each object and then processes them independently with multiple stages for the different sub-tasks. This leads to a complex pipeline to optimize and makes it hard to leverage the relationship constraints between multiple objects. In this work, we propose a novel Disentangled Object-Centric TRansformer (DOCTR) that explores object-centric representation to facilitate learning with multiple objects for the multiple sub-tasks in a unified manner. Each object is represented as a query, and a Transformer decoder is adapted to iteratively optimize all the queries involving their relationship. In particular, we introduce a semantic-geometry disentangled query (SGDQ) design that enables the query features to attend separately to semantic information and geometric information relevant to the corresponding sub-tasks. A hybrid bipartite matching module is employed to well use the supervisions from all the sub-tasks during training. Qualitative and quantitative experimental results demonstrate that our method achieves state-of-the-art performance on the challenging ScanNet dataset. Code is available at https://github.com/SAITPublic/DOCTR.
Event cameras, characterized by high temporal resolution, high dynamic range, low power consumption, and high pixel bandwidth, offer unique capabilities for object detection in specialized contexts. Despite these advantages, the inherent sparsity and asynchrony of event data pose challenges to existing object detection algorithms. Spiking Neural Networks (SNNs), inspired by the way the human brain codes and processes information, offer a potential solution to these difficulties. However, their performance in object detection using event cameras is limited in current implementations. In this paper, we propose the Spiking Fusion Object Detector (SFOD), a simple and efficient approach to SNN-based object detection. Specifically, we design a Spiking Fusion Module, achieving the first-time fusion of feature maps from different scales in SNNs applied to event cameras. Additionally, through integrating our analysis and experiments conducted during the pretraining of the backbone network on the NCAR dataset, we delve deeply into the impact of spiking decoding strategies and loss functions on model performance. Thereby, we establish state-of-the-art classification results based on SNNs, achieving 93.7\% accuracy on the NCAR dataset. Experimental results on the GEN1 detection dataset demonstrate that the SFOD achieves a state-of-the-art mAP of 32.1\%, outperforming existing SNN-based approaches. Our research not only underscores the potential of SNNs in object detection with event cameras but also propels the advancement of SNNs. Code is available at https://github.com/yimeng-fan/SFOD.
As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding. With the rapid deployment of deep neural networks for SOD tasks, the demand for high-quality training samples soars. The traditional, also reliable, way is manual labelling over the dense LiDAR point clouds and reference images. Though most public driving datasets adopt this strategy to provide SOD ground truth (GT), it is still expensive and time-consuming in practice. This paper introduces VRSO, a visual-centric approach for static object annotation. Experiments on the Waymo Open Dataset show that the mean reprojection error from VRSO annotation is only 2.6 pixels, around four times lower than the Waymo Open Dataset labels (10.6 pixels). VRSO is distinguished in low cost, high efficiency, and high quality: (1) It recovers static objects in 3D space with only camera images as input, and (2) manual annotation is barely involved since GT for SOD tasks is generated based on an automatic reconstruction and annotation pipeline.
Learning visual features from unlabeled images has proven successful for semantic categorization, often by mapping different $views$ of the same object to the same feature to achieve recognition invariance. However, visual recognition involves not only identifying $what$ an object is but also understanding $how$ it is presented. For example, seeing a car from the side versus head-on is crucial for deciding whether to stay put or jump out of the way. While unsupervised feature learning for downstream viewpoint reasoning is important, it remains under-explored, partly due to the lack of a standardized evaluation method and benchmarks. We introduce a new dataset of adjacent image triplets obtained from a viewpoint trajectory, without any semantic or pose labels. We benchmark both semantic classification and pose estimation accuracies on the same visual feature. Additionally, we propose a viewpoint trajectory regularization loss for learning features from unlabeled image triplets. Our experiments demonstrate that this approach helps develop a visual representation that encodes object identity and organizes objects by their poses, retaining semantic classification accuracy while achieving emergent global pose awareness and better generalization to novel objects. Our dataset and code are available at http://pwang.pw/trajSSL/.
We present T-Rex2, a highly practical model for open-set object detection. Previous open-set object detection methods relying on text prompts effectively encapsulate the abstract concept of common objects, but struggle with rare or complex object representation due to data scarcity and descriptive limitations. Conversely, visual prompts excel in depicting novel objects through concrete visual examples, but fall short in conveying the abstract concept of objects as effectively as text prompts. Recognizing the complementary strengths and weaknesses of both text and visual prompts, we introduce T-Rex2 that synergizes both prompts within a single model through contrastive learning. T-Rex2 accepts inputs in diverse formats, including text prompts, visual prompts, and the combination of both, so that it can handle different scenarios by switching between the two prompt modalities. Comprehensive experiments demonstrate that T-Rex2 exhibits remarkable zero-shot object detection capabilities across a wide spectrum of scenarios. We show that text prompts and visual prompts can benefit from each other within the synergy, which is essential to cover massive and complicated real-world scenarios and pave the way towards generic object detection. Model API is now available at \url{https://github.com/IDEA-Research/T-Rex}.
Determining the relative pose of a previously unseen object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically predict 3D translation utilizing the ground-truth object bounding box and approximate 3D rotation with a large number of discrete hypotheses. This strategy makes unrealistic assumptions about the availability of ground truth and incurs a computationally expensive process of scoring each hypothesis at test time. By contrast, we rethink the problem of relative pose estimation for unseen objects by presenting a Deep Voxel Matching Network (DVMNet++). Our method computes the relative object pose in a single pass, eliminating the need for ground-truth object bounding boxes and rotation hypotheses. We achieve open-set object detection by leveraging image feature embedding and natural language understanding as reference. The detection result is then employed to approximate the translation parameters and crop the object from the query image. For rotation estimation, we map the two RGB images, i.e., reference and cropped query, to their respective voxelized 3D representations. The resulting voxels are passed through a rotation estimation module, which aligns the voxels and computes the rotation in an end-to-end fashion by solving a least-squares problem. To enhance robustness, we introduce a weighted closest voxel algorithm capable of mitigating the impact of noisy voxels. We conduct extensive experiments on the CO3D, Objaverse, LINEMOD, and LINEMOD-O datasets, demonstrating that our approach delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods. Our code is released at https://github.com/sailor-z/DVMNet/.
Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP.
This paper proposes a data augmentation method for improving the robustness of driving object detectors against domain shift. Domain shift problem arises when there is a significant change between the distribution of the source data domain used in the training phase and that of the target data domain in the deployment phase. Domain shift is known as one of the most popular reasons resulting in the considerable drop in the performance of deep neural network models. In order to address this problem, one effective approach is to increase the diversity of training data. To this end, we propose a data synthesis module that can be utilized to train more robust and effective object detectors. By adopting YOLOv4 as a base object detector, we have witnessed a remarkable improvement in performance on both the source and target domain data. The code of this work is publicly available at https://github.com/tranleanh/haze-synthesis.
Driving is challenging in conditions like night, rain, and snow. Lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised Domain Adaptation (UDA) using large labeled clear-day datasets is a promising research direction in such cases. However, many UDA methods are trained with dominant scene backgrounds (e.g., roads, sky, sidewalks) that appear dramatically different across domains. As a result, they struggle to learn effective features of smaller and often sparse foreground objects (e.g., people, vehicles, signs). In this work, we improve UDA training by applying in-place image warping to focus on salient objects. We design instance-level saliency guidance to adaptively oversample object regions and undersample background areas, which reduces adverse effects from background context and enhances backbone feature learning. Our approach improves adaptation across geographies, lighting, and weather conditions, and is agnostic to the task (segmentation, detection), domain adaptation algorithm, saliency guidance, and underlying model architecture. Result highlights include +6.1 mAP50 for BDD100K Clear $\rightarrow$ DENSE Foggy, +3.7 mAP50 for BDD100K Day $\rightarrow$ Night, +3.0 mAP50 for BDD100K Clear $\rightarrow$ Rainy, and +6.3 mIoU for Cityscapes $\rightarrow$ ACDC. Besides, Our method adds minimal training memory and no additional inference latency. Code is available at https://github.com/ShenZheng2000/Instance-Warp
Existing object localization methods are tailored to locate specific classes of objects, relying heavily on abundant labeled data for model optimization. However, acquiring large amounts of labeled data is challenging in many real-world scenarios, significantly limiting the broader application of localization models. To bridge this research gap, this paper defines a novel task named Few-Shot Object Localization (FSOL), which aims to achieve precise localization with limited samples. This task achieves generalized object localization by leveraging a small number of labeled support samples to query the positional information of objects within corresponding images. To advance this field, we design an innovative high-performance baseline model. This model integrates a dual-path feature augmentation module to enhance shape association and gradient differences between supports and query images, alongside a self query module to explore the association between feature maps and query images. Experimental results demonstrate a significant performance improvement of our approach in the FSOL task, establishing an efficient benchmark for further research. All codes and data are available at https://github.com/Ryh1218/FSOL.