Junzhi Yu

Zhiheng Wu, Yue Lu, Xingyu Chen et al.

Open World Object Detection (OWOD) is a challenging computer vision problem that requires detecting unknown objects and gradually learning the identified unknown classes. However, it cannot distinguish unknown instances as multiple unknown classes. In this work, we propose a novel OWOD problem called Unknown-Classified Open World Object Detection (UC-OWOD). UC-OWOD aims to detect unknown instances and classify them into different unknown classes. Besides, we formulate the problem and devise a two-stage object detector to solve UC-OWOD. First, unknown label-aware proposal and unknown-discriminative classification head are used to detect known and unknown objects. Then, similarity-based unknown classification and unknown clustering refinement modules are constructed to distinguish multiple unknown classes. Moreover, two novel evaluation protocols are designed to evaluate unknown-class detection. Abundant experiments and visualizations prove the effectiveness of the proposed method. Code is available at https://github.com/JohnWuzh/UC-OWOD.

Lingyu Si, Hongwei Dong, Wenwen Qiang et al.

Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks. However, research on why transferred knowledge works has not been extensively explored. To address this issue, in this paper, we discover the correlation between feature discriminability and dimensional structure (DS) by analyzing and observing features extracted from simple and hard tasks. On this basis, we express DS using deep channel-wise correlation and intermediate spatial distribution, and propose a novel cross-modal knowledge distillation (CMKD) method for better supervised cross-modal learning (CML) performance. The proposed method enforces output features to be channel-wise independent and intermediate ones to be uniformly distributed, thereby learning semantically irrelevant features from the hard task to boost its accuracy. This is especially useful in specific applications where the performance gap between dual modalities is relatively large. Furthermore, we collect a real-world CML dataset to promote community development. The dataset contains more than 10,000 paired optical and radar images and is continuously being updated. Experimental results on real-world and benchmark datasets validate the effectiveness of the proposed method.

Xingyu Chen, Junzhi Yu, Shihan Kong et al.

Object detection has been vigorously investigated for years but fast accurate detection for real-world scenes remains a very challenging problem. Overcoming drawbacks of single-stage detectors, we take aim at precisely detecting objects for static and temporal scenes in real time. Firstly, as a dual refinement mechanism, a novel anchor-offset detection is designed, which includes an anchor refinement, a feature location refinement, and a deformable detection head. This new detection mode is able to simultaneously perform two-step regression and capture accurate object features. Based on the anchor-offset detection, a dual refinement network (DRNet) is developed for high-performance static detection, where a multi-deformable head is further designed to leverage contextual information for describing objects. As for temporal detection in videos, temporal refinement networks (TRNet) and temporal dual refinement networks (TDRNet) are developed by propagating the refinement information across time. We also propose a soft refinement strategy to temporally match object motion with the previous refinement. Our proposed methods are evaluated on PASCAL VOC, COCO, and ImageNet VID datasets. Extensive comparisons on static and temporal detection verify the superiority of DRNet, TRNet, and TDRNet. Consequently, our developed approaches run in a fairly fast speed, and in the meantime achieve a significantly enhanced detection accuracy, i.e., 84.4% mAP on VOC 2007, 83.6% mAP on VOC 2012, 69.4% mAP on VID 2017, and 42.4% AP on COCO. Ultimately, producing encouraging results, our methods are applied to online underwater object detection and grasping with an autonomous system. Codes are publicly available at https://github.com/SeanChenxy/TDRN.

Xingyu Chen, Junzhi Yu, Zhengxing Wu

Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few approaches can achieve \emph{real-time online} object detection in videos. In this paper, based on attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for real-world detection. Distinct from previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLSTM, and design a novel structure including a low-level temporal unit as well as a high-level one (LH-TU) for multi-scale feature maps. Moreover, we develop a creative temporal analysis unit, namely, attentional ConvLSTM (AC-LSTM), in which a temporal attention mechanism is specially tailored for background suppression and scale suppression while a ConvLSTM integrates attention-aware features across time. An association loss and a multi-step training are designed for temporal coherence. Besides, an online tubelet analysis (OTA) is exploited for identification. Our framework is evaluated on ImageNet VID dataset and 2DMOT15 dataset. Extensive comparisons on the detection and tracking capability validate the superiority of the proposed approach. Consequently, the developed TSSD-OTA achieves a fast speed and an overall competitive performance in terms of detection and tracking. Finally, a real-world maneuver is conducted for underwater object grasping. The source code is publicly available at https://github.com/SeanChenxy/TSSD-OTA.

Xingyu Chen, Junzhi Yu, Shihan Kong et al.

Low visual quality has prevented underwater robotic vision from a wide range of applications. Although several algorithms have been developed, real-time and adaptive methods are deficient for real-world tasks. In this paper, we address this difficulty based on generative adversarial networks (GAN), and propose a GAN-based restoration scheme (GAN-RS). In particular, we develop a multi-branch discriminator including an adversarial branch and a critic branch for the purpose of simultaneously preserving image content and removing underwater noise. In addition to adversarial learning, a novel dark channel prior loss also promotes the generator to produce realistic vision. More specifically, an underwater index is investigated to describe underwater properties, and a loss function based on the underwater index is designed to train the critic branch for underwater noise suppression. Through extensive comparisons on visual quality and feature restoration, we confirm the superiority of the proposed approach. Consequently, the GAN-RS can adaptively improve underwater visual quality in real time and induce an overall superior restoration performance. Finally, a real-world experiment is conducted on the seabed for grasping marine products, and the results are quite promising. The source code is publicly available at https://github.com/SeanChenxy/GAN_RS.

Shaoan Wang, Jiazhao Zhang, Minghan Li et al.

Embodied visual tracking is a fundamental skill in Embodied AI, enabling an agent to follow a specific target in dynamic environments using only egocentric vision. This task is inherently challenging as it requires both accurate target recognition and effective trajectory planning under conditions of severe occlusion and high scene dynamics. Existing approaches typically address this challenge through a modular separation of recognition and planning. In this work, we propose TrackVLA, a Vision-Language-Action (VLA) model that learns the synergy between object recognition and trajectory planning. Leveraging a shared LLM backbone, we employ a language modeling head for recognition and an anchor-based diffusion model for trajectory planning. To train TrackVLA, we construct an Embodied Visual Tracking Benchmark (EVT-Bench) and collect diverse difficulty levels of recognition samples, resulting in a dataset of 1.7 million samples. Through extensive experiments in both synthetic and real-world environments, TrackVLA demonstrates SOTA performance and strong generalizability. It significantly outperforms existing methods on public benchmarks in a zero-shot manner while remaining robust to high dynamics and occlusion in real-world scenarios at 10 FPS inference speed. Our project page is: https://pku-epic.github.io/TrackVLA-web.

Qing Jiang, Xingyu Chen, Zhaoyang Zeng et al.

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding box prediction task, offering limited interpretability and struggling to reject expressions with no matching object. In this work, we propose Rex-Thinker, a model that formulates object referring as an explicit CoT reasoning task. Given a referring expression, we first identify all candidate object instances corresponding to the referred object category. Rex-Thinker then performs step-by-step reasoning over each candidate to assess whether it matches the given expression, before making a final prediction. To support this paradigm, we construct a large-scale CoT-style referring dataset named HumanRef-CoT by prompting GPT-4o on the HumanRef dataset. Each reasoning trace follows a structured planning, action, and summarization format, enabling the model to learn decomposed, interpretable reasoning over object candidates. We then train Rex-Thinker in two stages: a cold-start supervised fine-tuning phase to teach the model how to perform structured reasoning, followed by GRPO-based RL learning to improve accuracy and generalization. Experiments show that our approach outperforms standard baselines in both precision and interpretability on in-domain evaluation, while also demonstrating improved ability to reject hallucinated outputs and strong generalization in out-of-domain settings.

Xingyu Chen, Zhuheng Song, Xiaoke Jiang et al.

Existing approaches of hand reconstruction predominantly adhere to a multi-stage framework, encompassing detection, left-right classification, and pose estimation. This paradigm induces redundant computation and cumulative errors. In this work, we propose HandOS, an end-to-end framework for 3D hand reconstruction. Our central motivation lies in leveraging a frozen detector as the foundation while incorporating auxiliary modules for 2D and 3D keypoint estimation. In this manner, we integrate the pose estimation capacity into the detection framework, while at the same time obviating the necessity of using the left-right category as a prerequisite. Specifically, we propose an interactive 2D-3D decoder, where 2D joint semantics is derived from detection cues while 3D representation is lifted from those of 2D joints. Furthermore, hierarchical attention is designed to enable the concurrent modeling of 2D joints, 3D vertices, and camera translation. Consequently, we achieve an end-to-end integration of hand detection, 2D pose estimation, and 3D mesh reconstruction within a one-stage framework, so that the above multi-stage drawbacks are overcome. Meanwhile, the HandOS reaches state-of-the-art performances on public benchmarks, e.g., 5.0 PA-MPJPE on FreiHand and 64.6\% PCK@0.05 on HInt-Ego4D. Project page: idea-research.github.io/HandOSweb.

Zhihao Wang, Jianxiong Li, Jinliang Zheng et al. · tsinghua

Vision-Language-Action (VLA) models have achieved notable success but often struggle with limited generalizations. To address this, integrating generalized Vision-Language Models (VLMs) as assistants to VLAs has emerged as a popular solution. However, current approaches often combine these models in rigid, sequential structures: using VLMs primarily for high-level scene understanding and task planning, and VLAs merely as executors of lower-level actions, leading to ineffective collaboration and poor grounding challenges. In this paper, we propose an embodied agent framework, PhysiAgent, tailored to operate effectively in physical environments. By incorporating monitor, memory, self-reflection mechanisms, and lightweight off-the-shelf toolboxes, PhysiAgent offers an autonomous scaffolding framework to prompt VLMs to organize different components based on real-time proficiency feedback from VLAs to maximally exploit VLAs' capabilities. Experimental results demonstrate significant improvements in task-solving performance on complex real-world robotic tasks, showcasing effective self-regulation of VLMs, coherent tool collaboration, and adaptive evolution of the framework during execution. PhysiAgent makes practical and pioneering efforts to integrate VLMs and VLAs, effectively grounding embodied agent frameworks in real-world settings.

Qing Jiang, Junan Huo, Xingyu Chen et al.

Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low recall rate, duplicate predictions, coordinate misalignment, etc. In this work, we bridge this gap and propose Rex-Omni, a 3B-scale MLLM that achieves state-of-the-art object perception performance. On benchmarks like COCO and LVIS, Rex-Omni attains performance comparable to or exceeding regression-based models (e.g., DINO, Grounding DINO) in a zero-shot setting. This is enabled by three key designs: 1) Task Formulation: we use special tokens to represent quantized coordinates from 0 to 999, reducing the model's learning difficulty and improving token efficiency for coordinate prediction; 2) Data Engines: we construct multiple data engines to generate high-quality grounding, referring, and pointing data, providing semantically rich supervision for training; \3) Training Pipelines: we employ a two-stage training process, combining supervised fine-tuning on 22 million data with GRPO-based reinforcement post-training. This RL post-training leverages geometry-aware rewards to effectively bridge the discrete-to-continuous coordinate prediction gap, improve box accuracy, and mitigate undesirable behaviors like duplicate predictions that stem from the teacher-guided nature of the initial SFT stage. Beyond conventional detection, Rex-Omni's inherent language understanding enables versatile capabilities such as object referring, pointing, visual prompting, GUI grounding, spatial referring, OCR and key-pointing, all systematically evaluated on dedicated benchmarks. We believe that Rex-Omni paves the way for more versatile and language-aware visual perception systems.

Rui Chen, Xingyu Chen, Shaoan Wang et al.

Event cameras output event streams as sparse, asynchronous data with microsecond-level temporal resolution, enabling visual perception with low latency and a high dynamic range. While existing Multimodal Large Language Models (MLLMs) have achieved significant success in understanding and analyzing RGB video content, they either fail to interpret event streams effectively or remain constrained to very short sequences. In this paper, we introduce LET-US, a framework for long event-stream--text comprehension that employs an adaptive compression mechanism to reduce the volume of input events while preserving critical visual details. LET-US thus establishes a new frontier in cross-modal inferential understanding over extended event sequences. To bridge the substantial modality gap between event streams and textual representations, we adopt a two-stage optimization paradigm that progressively equips our model with the capacity to interpret event-based scenes. To handle the voluminous temporal information inherent in long event streams, we leverage text-guided cross-modal queries for feature reduction, augmented by hierarchical clustering and similarity computation to distill the most representative event features. Moreover, we curate and construct a large-scale event-text aligned dataset to train our model, achieving tighter alignment of event features within the LLM embedding space. We also develop a comprehensive benchmark covering a diverse set of tasks -- reasoning, captioning, classification, temporal localization and moment retrieval. Experimental results demonstrate that LET-US outperforms prior state-of-the-art MLLMs in both descriptive accuracy and semantic comprehension on long-duration event streams. All datasets, codes, and models will be publicly available.

Zhanhua Xin, Zhihao Wang, Shenghao Zhang et al.

In the field of multi-sensor fusion for simultaneous localization and mapping (SLAM), monocular cameras and IMUs are widely used to build simple and effective visual-inertial systems. However, limited research has explored the integration of motor-encoder devices to enhance SLAM performance. By incorporating such devices, it is possible to significantly improve active capability and field of view (FOV) with minimal additional cost and structural complexity. This paper proposes a novel visual-inertial-encoder tightly coupled odometry (VIEO) based on a ViDAR (Video Detection and Ranging) device. A ViDAR calibration method is introduced to ensure accurate initialization for VIEO. In addition, a platform motion decoupled active SLAM method based on deep reinforcement learning (DRL) is proposed. Experimental data demonstrate that the proposed ViDAR and the VIEO algorithm significantly increase cross-frame co-visibility relationships compared to its corresponding visual-inertial odometry (VIO) algorithm, improving state estimation accuracy. Additionally, the DRL-based active SLAM algorithm, with the ability to decouple from platform motion, can increase the diversity weight of the feature points and further enhance the VIEO algorithm's performance. The proposed methodology sheds fresh insights into both the updated platform design and decoupled approach of active SLAM systems in complex environments.

Shuaizheng Yan, Xingyu Chen, Zhengxing Wu et al.

Robust vision restoration of underwater images remains a challenge. Owing to the lack of well-matched underwater and in-air images, unsupervised methods based on the cyclic generative adversarial framework have been widely investigated in recent years. However, when using an end-to-end unsupervised approach with only unpaired image data, mode collapse could occur, and the color correction of the restored images is usually poor. In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater and in-air images. For effective color correction and quality enhancement, an underwater image degeneration model must be explicitly constructed based on the optically unambiguous physics law. Thus, we employ the Jaffe-McGlamery degeneration theory to design a generator and use neural networks to model the process of underwater visual degeneration. Furthermore, we impose physical constraints on the scene depth and degeneration factors for backscattering estimation to avoid the vanishing gradient problem during the training of the hybrid physical-neural model. Experimental results show that the proposed method can be used to perform high-quality restoration of unconstrained underwater images without supervision. On multiple benchmarks, the proposed method outperforms several state-of-the-art supervised and unsupervised approaches. We demonstrate that our method yields encouraging results in real-world applications.

Xingyu Chen, Yue Lu, Zhengxing Wu et al.

Underwater robotic perception usually requires visual restoration and object detection, both of which have been studied for many years. Meanwhile, data domain has a huge impact on modern data-driven leaning process. However, exactly indicating domain effect, the relation between restoration and detection remains unclear. In this paper, we generally investigate the relation of quality-diverse data domain to detection performance. In the meantime, we unveil how visual restoration contributes to object detection in real-world underwater scenes. According to our analysis, five key discoveries are reported: 1) Domain quality has an ignorable effect on within-domain convolutional representation and detection accuracy; 2) low-quality domain leads to higher generalization ability in cross-domain detection; 3) low-quality domain can hardly be well learned in a domain-mixed learning process; 4) degrading recall efficiency, restoration cannot improve within-domain detection accuracy; 5) visual restoration is beneficial to detection in the wild by reducing the domain shift between training data and real-world scenes. Finally, as an illustrative example, we successfully perform underwater object detection with an aquatic robot.

Xingyu Chen, Zhengxing Wu, Junzhi Yu et al.

Video object detection (VID) has been vigorously studied for years but almost all literature adopts a static accuracy-based evaluation, i.e., average precision (AP). From a robotic perspective, the importance of recall continuity and localization stability is equal to that of accuracy, but the AP is insufficient to reflect detectors' performance across time. In this paper, non-reference assessments are proposed for continuity and stability based on object tracklets. These temporal evaluations can serve as supplements to static AP. Further, we develop an online tracklet refinement for improving detectors' temporal performance through short tracklet suppression, fragment filling, and temporal location fusion. In addition, we propose a small-overlap suppression to extend VID methods to single object tracking (SOT) task so that a flexible SOT-by-detection framework is then formed. Extensive experiments are conducted on ImageNet VID dataset and real-world robotic tasks, where the superiority of our proposed approaches are validated and verified. Codes will be publicly available.