Xingyu Chen

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.

Yulei Qin, Xingyu Chen, Chao Chen et al.

Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the ``realistic" prototype. Then, the intra-class distance between web instances and ``realistic" prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.

Dongli Tan, Jiang-Jiang Liu, Xingyu Chen et al. · tencent-ai

Modeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its efficiency, which is crucial for realworld applications. In this paper, we propose an efficient structure named Efficient Correspondence Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner, which significantly improves the efficiency of functional correspondence model. To achieve this, multiple transformer blocks are stage-wisely connected to gradually refine the predicted coordinates upon a shared multi-scale feature extraction network. Given a pair of images and for arbitrary query coordinates, all the correspondences are predicted within a single feed-forward pass. We further propose an adaptive query-clustering strategy and an uncertainty-based outlier detection module to cooperate with the proposed framework for faster and better predictions. Experiments on various sparse and dense matching tasks demonstrate the superiority of our method in both efficiency and effectiveness against existing state-of-the-arts.

Yulei Qin, Xingyu Chen, Yunhang Shen et al.

Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with challenges from label noise, and they have limited assumptions on clean samples under various noise. For instance, web images retrieved with queries of tiger cat (a cat species) and drumstick (a musical instrument) are almost dominated by images of tigers and chickens, which exacerbates the challenge of fine-grained visual concept learning. In this case, exploiting both web images and their associated texts is a requisite solution to combat real-world noise. In this paper, we propose Cross-modality Aligned Prototypes (CAPro), a unified prototypical contrastive learning framework to learn visual representations with correct semantics. For one thing, we leverage textual prototypes, which stem from the distinct concept definition of classes, to select clean images by text matching and thus disambiguate the formation of visual prototypes. For another, to handle missing and mismatched noisy texts, we resort to the visual feature space to complete and enhance individual texts and thereafter improve text matching. Such semantically aligned visual prototypes are further polished up with high-quality samples, and engaged in both cluster regularization and noise removal. Besides, we propose collective bootstrapping to encourage smoother and wiser label reference from appearance-similar instances in a manner of dictionary look-up. Extensive experiments on WebVision1k and NUS-WIDE (Web) demonstrate that CAPro well handles realistic noise under both single-label and multi-label scenarios. CAPro achieves new state-of-the-art performance and exhibits robustness to open-set recognition. Codes are available at https://github.com/yuleiqin/capro.

Yue Chen, Xingyu Chen, Xuan Wang et al.

Neural Radiance Fields (NeRF) have achieved photorealistic novel views synthesis; however, the requirement of accurate camera poses limits its application. Despite analysis-by-synthesis extensions for jointly learning neural 3D representations and registering camera frames exist, they are susceptible to suboptimal solutions if poorly initialized. We propose L2G-NeRF, a Local-to-Global registration method for bundle-adjusting Neural Radiance Fields: first, a pixel-wise flexible alignment, followed by a frame-wise constrained parametric alignment. Pixel-wise local alignment is learned in an unsupervised way via a deep network which optimizes photometric reconstruction errors. Frame-wise global alignment is performed using differentiable parameter estimation solvers on the pixel-wise correspondences to find a global transformation. Experiments on synthetic and real-world data show that our method outperforms the current state-of-the-art in terms of high-fidelity reconstruction and resolving large camera pose misalignment. Our module is an easy-to-use plugin that can be applied to NeRF variants and other neural field applications. The Code and supplementary materials are available at https://rover-xingyu.github.io/L2G-NeRF/.

Yue Chen, Xuan Wang, Xingyu Chen et al.

Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications. But the practice is severely limited by high computational costs in the rendering process. To solve this problem, we propose the UV Volumes, a new approach that can render an editable free-view video of a human performer in real-time. It separates the high-frequency (i.e., non-smooth) human appearance from the 3D volume, and encodes them into 2D neural texture stacks (NTS). The smooth UV volumes allow much smaller and shallower neural networks to obtain densities and texture coordinates in 3D while capturing detailed appearance in 2D NTS. For editability, the mapping between the parameterized human model and the smooth texture coordinates allows us a better generalization on novel poses and shapes. Furthermore, the use of NTS enables interesting applications, e.g., retexturing. Extensive experiments on CMU Panoptic, ZJU Mocap, and H36M datasets show that our model can render 960 x 540 images in 30FPS on average with comparable photo-realism to state-of-the-art methods. The project and supplementary materials are available at https://fanegg.github.io/UV-Volumes.

Xingyu Chen, Ruiqi Zhang, Lin Liu

Higher-order $U$-statistics abound in fields such as statistics, machine learning, and computer science, but are known to be highly time-consuming to compute in practice. Despite their widespread appearance, a comprehensive study of their computational complexity is surprisingly lacking. This paper aims to fill this gap by presenting several results related to the computational aspect of $U$-statistics. First, we derive a useful decomposition from a $m$-th order $U$-statistic to a linear combination of $V$-statistics with orders not exceeding $m$, which are generally more feasible to compute. Second, we explore the connection between exactly computing $V$-statistics and Einstein summation, a tool often used in computational mathematics and quantum computing to accelerate tensor computations. Third, we provide an optimistic estimate of the time complexity for exactly computing $U$-statistics, based on the treewidth of a particular graph associated with the $U$-statistic kernel. The above ingredients lead to (1) a new, much more runtime-efficient algorithm to exactly compute general higher-order $U$-statistics, and (2) a more streamlined characterization of runtime complexity of computing $U$-statistics. We develop an accompanying open-source package called \texttt{u-stats} in both Python (https://github.com/zrq1706/U-Statistics-Python) and R (https://github.com/cxy0714/U-Statistics-R). We demonstrate through three examples in statistics that \texttt{u-stats} achieves impressive runtime performance compared to existing benchmarks. This paper also aspires to achieve two goals: (1) to capture the interest of researchers in both statistics and other related areas to further advance the algorithmic development of $U$-statistics and (2) to lift the burden of implementing higher-order $U$-statistics from practitioners.

Xingyu Chen, Yu Deng, Baoyuan Wang

Generating images with both photorealism and multiview 3D consistency is crucial for 3D-aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the photorealism via CNN-based 2D super-resolution can break the strict 3D consistency, while keeping the 3D consistency by learning high-resolution 3D representations for direct rendering often compromises image quality. In this paper, we propose a novel learning strategy, namely 3D-to-2D imitation, which enables a 3D-aware GAN to generate high-quality images while maintaining their strict 3D consistency, by letting the images synthesized by the generator's 3D rendering branch to mimic those generated by its 2D super-resolution branch. We also introduce 3D-aware convolutions into the generator for better 3D representation learning, which further improves the image generation quality. With the above strategies, our method reaches FID scores of 5.4 and 4.3 on FFHQ and AFHQ-v2 Cats, respectively, at 512x512 resolution, largely outperforming existing 3D-aware GANs using direct 3D rendering and coming very close to the previous state-of-the-art method that leverages 2D super-resolution. Project website: https://seanchenxy.github.io/Mimic3DWeb.

Xiaochen Zheng, Xingyu Chen, Manuel Schürch et al.

Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these methods are less effective for time series forecasting, as optimization of instance discrimination is not directly applicable to predicting the future state from the historical context. To address these limitations, we propose SimTS, a simple representation learning approach for improving time series forecasting by learning to predict the future from the past in the latent space. SimTS exclusively uses positive pairs and does not depend on negative pairs or specific characteristics of a given time series. In addition, we show the shortcomings of the current contrastive learning framework used for time series forecasting through a detailed ablation study. Overall, our work suggests that SimTS is a promising alternative to other contrastive learning approaches for time series forecasting.

Xingyu Chen, Jianru Xue, Jianwu Fang et al.

In this paper, we propose a lightweight system, RDS-SLAM, based on ORB-SLAM2, which can accurately estimate poses and build semantic maps at object level for dynamic scenarios in real time using only one commonly used Intel Core i7 CPU. In RDS-SLAM, three major improvements, as well as major architectural modifications, are proposed to overcome the limitations of ORB-SLAM2. Firstly, it adopts a lightweight object detection neural network in key frames. Secondly, an efficient tracking and prediction mechanism is embedded into the system to remove the feature points belonging to movable objects in all incoming frames. Thirdly, a semantic octree map is built by probabilistic fusion of detection and tracking results, which enables a robot to maintain a semantic description at object level for potential interactions in dynamic scenarios. We evaluate RDS-SLAM in TUM RGB-D dataset, and experimental results show that RDS-SLAM can run with 30.3 ms per frame in dynamic scenarios using only an Intel Core i7 CPU, and achieves comparable accuracy compared with the state-of-the-art SLAM systems which heavily rely on both Intel Core i7 CPUs and powerful GPUs.

Xingyu Chen, Thomas H. Li, Ruonan Zhang et al.

We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models. The high generalizability of our methods is achieved by solving the fundamental and ubiquitous problems in photometric loss function. In particular, from the perspective of spatial frequency, we first propose Ambiguity-Masking to suppress the incorrect supervision under photometric loss at specific object boundaries, the cause of which could be traced to pixel-level ambiguity. Second, we present a novel frequency-adaptive Gaussian low-pass filter, designed to robustify the photometric loss in high-frequency regions. We are the first to propose blurring images to improve depth estimators with an interpretable analysis. Both modules are lightweight, adding no parameters and no need to manually change the network structures. Experiments show that our methods provide performance boosts to a large number of existing models, including those who claimed state-of-the-art, while introducing no extra inference computation at all.

Xiyuan Wei, Fanjiang Ye, Ori Yonay et al.

Existing studies of training state-of-the-art Contrastive Language-Image Pretraining (CLIP) models on large-scale data involve hundreds of or even thousands of GPUs due to the requirement of a large batch size. However, such a large amount of resources is not accessible to most people. While advanced compositional optimization techniques for optimizing global contrastive losses have been demonstrated effective for removing the requirement of large batch size, their performance on large-scale data remains underexplored and not optimized. To bridge the gap, this paper explores several aspects of CLIP training with limited resources (e.g., up to tens of GPUs). First, we introduce FastCLIP, a general CLIP training framework built on advanced compositional optimization techniques while designed and optimized for the distributed setting. Our framework is equipped with an efficient gradient reduction strategy to reduce communication overhead. Second, to further boost training efficiency, we investigate three components of the framework from an optimization perspective: the schedule of the inner learning rate, the update rules of the temperature parameter and the model parameters, respectively. Experiments on different strategies for each component shed light on how to conduct CLIP training more efficiently. Finally, we benchmark the performance of FastCLIP and the state-of-the-art training baseline (OpenCLIP) on different compute scales up to 32 GPUs on 8 nodes, and three data scales ranging from 2.7 million, 9.1 million to 315 million image-text pairs to demonstrate the significant improvement of FastCLIP in the resource-limited setting. We release the code of FastCLIP at https://github.com/Optimization-AI/fast_clip .

Yu Deng, Duomin Wang, Xiaohang Ren et al.

Existing one-shot 4D head synthesis methods usually learn from monocular videos with the aid of 3DMM reconstruction, yet the latter is evenly challenging which restricts them from reasonable 4D head synthesis. We present a method to learn one-shot 4D head synthesis via large-scale synthetic data. The key is to first learn a part-wise 4D generative model from monocular images via adversarial learning, to synthesize multi-view images of diverse identities and full motions as training data; then leverage a transformer-based animatable triplane reconstructor to learn 4D head reconstruction using the synthetic data. A novel learning strategy is enforced to enhance the generalizability to real images by disentangling the learning process of 3D reconstruction and reenactment. Experiments demonstrate our superiority over the prior art.

Han Wang, Jiayuan Zhang, Lipeng Wan et al.

Manipulation relationship detection (MRD) aims to guide the robot to grasp objects in the right order, which is important to ensure the safety and reliability of grasping in object stacked scenes. Previous works infer manipulation relationship by deep neural network trained with data collected from a predefined view, which has limitation in visual dislocation in unstructured environments. Multi-view data provide more comprehensive information in space, while a challenge of multi-view MRD is domain shift. In this paper, we propose a novel multi-view fusion framework, namely multi-view MRD network (MMRDN), which is trained by 2D and 3D multi-view data. We project the 2D data from different views into a common hidden space and fit the embeddings with a set of Von-Mises-Fisher distributions to learn the consistent representations. Besides, taking advantage of position information within the 3D data, we select a set of $K$ Maximum Vertical Neighbors (KMVN) points from the point cloud of each object pair, which encodes the relative position of these two objects. Finally, the features of multi-view 2D and 3D data are concatenated to predict the pairwise relationship of objects. Experimental results on the challenging REGRAD dataset show that MMRDN outperforms the state-of-the-art methods in multi-view MRD tasks. The results also demonstrate that our model trained by synthetic data is capable to transfer to real-world scenarios.

Xihe Yang, Xingyu Chen, Daiheng Gao et al.

As for human avatar reconstruction, contemporary techniques commonly necessitate the acquisition of costly data and struggle to achieve satisfactory results from a small number of casual images. In this paper, we investigate this task from a few-shot unconstrained photo album. The reconstruction of human avatars from such data sources is challenging because of limited data amount and dynamic articulated poses. For handling dynamic data, we integrate a skinning mechanism with deep marching tetrahedra (DMTet) to form a drivable tetrahedral representation, which drives arbitrary mesh topologies generated by the DMTet for the adaptation of unconstrained images. To effectively mine instructive information from few-shot data, we devise a two-phase optimization method with few-shot reference and few-shot guidance. The former focuses on aligning avatar identity with reference images, while the latter aims to generate plausible appearances for unseen regions. Overall, our framework, called HaveFun, can undertake avatar reconstruction, rendering, and animation. Extensive experiments on our developed benchmarks demonstrate that HaveFun exhibits substantially superior performance in reconstructing the human body and hand. Project website: https://seanchenxy.github.io/HaveFunWeb/.

Jiang-Tian Zhai, Qi Zhang, Tong Wu et al.

Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by textagnostic and redundant regions obtained with the frozen detectors, or failing to scale further due to its heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for cross-modal understanding tasks without any extra gold data. SLAN consists of a region filter and a region adaptor to localize regions of interest conditioned on different texts. By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance. With detailed region-word alignments, SLAN can be easily generalized to many downstream tasks. It achieves fairly competitive results on five cross-modal understanding tasks (e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval, surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot and fine-tuned transferability to two localization tasks.

Chunnan Wang, Xingyu Chen, Chengyue Wu et al.

Automatic Time Series Forecasting (TSF) model design which aims to help users to efficiently design suitable forecasting model for the given time series data scenarios, is a novel research topic to be urgently solved. In this paper, we propose AutoTS algorithm trying to utilize the existing design skills and design efficient search methods to effectively solve this problem. In AutoTS, we extract effective design experience from the existing TSF works. We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks. Considering the huge search space, in AutoTS, we propose a two-stage pruning strategy to reduce the search difficulty and improve the search efficiency. In addition, in AutoTS, we introduce the knowledge graph to reveal associations between module options. We make full use of these relational information to learn higher-level features of each module option, so as to further improve the search quality. Extensive experimental results show that AutoTS is well-suited for the TSF area. It is more efficient than the existing neural architecture search algorithms, and can quickly design powerful TSF model better than the manually designed ones.

Xingyu Chen, Xiaochen Zheng, Amina Mollaysa et al.

Irregular multivariate time series data is characterized by varying time intervals between consecutive observations of measured variables/signals (i.e., features) and varying sampling rates (i.e., recordings/measurement) across these features. Modeling time series while taking into account these irregularities is still a challenging task for machine learning methods. Here, we introduce TADA, a Two-stageAggregation process with Dynamic local Attention to harmonize time-wise and feature-wise irregularities in multivariate time series. In the first stage, the irregular time series undergoes temporal embedding (TE) using all available features at each time step. This process preserves the contribution of each available feature and generates a fixed-dimensional representation per time step. The second stage introduces a dynamic local attention (DLA) mechanism with adaptive window sizes. DLA aggregates time recordings using feature-specific windows to harmonize irregular time intervals capturing feature-specific sampling rates. Then hierarchical MLP mixer layers process the output of DLA through multiscale patching to leverage information at various scales for the downstream tasks. TADA outperforms state-of-the-art methods on three real-world datasets, including the latest MIMIC IV dataset, and highlights its effectiveness in handling irregular multivariate time series and its potential for various real-world applications.

Xingyu Chen, Yufeng Liu, Yajiao Dong et al.

In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Specifically, for 2D encoding, we propose lightweight yet effective stacked structures. Regarding 3D decoding, we provide an efficient graph operator, namely depth-separable spiral convolution. Moreover, we present a novel feature lifting module for bridging the gap between 2D and 3D representations. This module begins with a map-based position regression (MapReg) block to integrate the merits of both heatmap encoding and position regression paradigms for improved 2D accuracy and temporal coherence. Furthermore, MapReg is followed by pose pooling and pose-to-vertex lifting approaches, which transform 2D pose encodings to semantic features of 3D vertices. Overall, our hand reconstruction framework, called MobRecon, comprises affordable computational costs and miniature model size, which reaches a high inference speed of 83FPS on Apple A14 CPU. Extensive experiments on popular datasets such as FreiHAND, RHD, and HO3Dv2 demonstrate that our MobRecon achieves superior performance on reconstruction accuracy and temporal coherence. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

Xingyu Chen, Yufeng Liu, Chongyang Ma et al.

Recent years have witnessed significant progress in 3D hand mesh recovery. Nevertheless, because of the intrinsic 2D-to-3D ambiguity, recovering camera-space 3D information from a single RGB image remains challenging. To tackle this problem, we divide camera-space mesh recovery into two sub-tasks, i.e., root-relative mesh recovery and root recovery. First, joint landmarks and silhouette are extracted from a single input image to provide 2D cues for the 3D tasks. In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues. Such generated 3D mesh coordinates are expressed relative to a root position, i.e., wrist of the hand. In the root recovery task, the root position is registered to the camera space by aligning the generated 3D mesh back to 2D cues, thereby completing cameraspace 3D mesh recovery. Our pipeline is novel in that (1) it explicitly makes use of known semantic relations among joints and (2) it exploits 1D projections of the silhouette and mesh to achieve robust registration. Extensive experiments on popular datasets such as FreiHAND, RHD, and Human3.6M demonstrate that our approach achieves stateof-the-art performance on both root-relative mesh recovery and root recovery. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

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.

Tianhe Ren, Yihao Chen, Qing Jiang et al.

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.

Ke Ji, Jiahao Xu, Tian Liang et al.

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the observation of Prefix Self-Consistency -- the shared initial reasoning steps across diverse solution trajectories -- to enhance LLM reasoning efficiency. By training exclusively on the initial prefix substrings (as few as 8 tokens), UPFT removes the need for labeled data or exhaustive sampling. Experiments on reasoning benchmarks show that UPFT matches the performance of supervised methods such as Rejection Sampling Fine-Tuning, while reducing training time by 75% and sampling cost by 99%. Further analysis reveals that errors tend to appear in later stages of the reasoning process and that prefix-based training preserves the model's structural knowledge. This work demonstrates how minimal unsupervised fine-tuning can unlock substantial reasoning gains in LLMs, offering a scalable and resource-efficient alternative to conventional approaches.

Runsen Xu, Weiyao Wang, Hao Tang et al.

Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for robotics and other real-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with robust multi-frame spatial understanding by integrating depth perception, visual correspondence, and dynamic perception. Central to our approach is the MultiSPA dataset, a novel, large-scale collection of more than 27 million samples spanning diverse 3D and 4D scenes. Alongside MultiSPA, we introduce a comprehensive benchmark that tests a wide spectrum of spatial tasks under uniform metrics. Our resulting model, Multi-SpatialMLLM, achieves significant gains over baselines and proprietary systems, demonstrating scalable, generalizable multi-frame reasoning. We further observe multi-task benefits and early indications of emergent capabilities in challenging scenarios, and showcase how our model can serve as a multi-frame reward annotator for robotics.

Weiyao Wang, Pierre Gleize, Hao Tang et al.

Neural Radiance Fields (NeRF) exhibit remarkable performance for Novel View Synthesis (NVS) given a set of 2D images. However, NeRF training requires accurate camera pose for each input view, typically obtained by Structure-from-Motion (SfM) pipelines. Recent works have attempted to relax this constraint, but they still often rely on decent initial poses which they can refine. Here we aim at removing the requirement for pose initialization. We present Incremental CONfidence (ICON), an optimization procedure for training NeRFs from 2D video frames. ICON only assumes smooth camera motion to estimate initial guess for poses. Further, ICON introduces ``confidence": an adaptive measure of model quality used to dynamically reweight gradients. ICON relies on high-confidence poses to learn NeRF, and high-confidence 3D structure (as encoded by NeRF) to learn poses. We show that ICON, without prior pose initialization, achieves superior performance in both CO3D and HO3D versus methods which use SfM pose.

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.

Xingyu Chen, Hanyu Wu, Sikai Wu et al.

Human-to-humanoid imitation learning aims to learn a humanoid whole-body controller from human motion. Motion retargeting is a crucial step in enabling robots to acquire reference trajectories when exploring locomotion skills. However, current methods focus on motion retargeting frame by frame, which lacks scalability. Could we directly convert large-scale human motion into robot-executable motion through a more efficient approach? To address this issue, we propose Implicit Kinodynamic Motion Retargeting (IKMR), a novel efficient and scalable retargeting framework that considers both kinematics and dynamics. In kinematics, IKMR pretrains motion topology feature representation and a dual encoder-decoder architecture to learn a motion domain mapping. In dynamics, IKMR integrates imitation learning with the motion retargeting network to refine motion into physically feasible trajectories. After fine-tuning using the tracking results, IKMR can achieve large-scale physically feasible motion retargeting in real time, and a whole-body controller could be directly trained and deployed for tracking its retargeted trajectories. We conduct our experiments both in the simulator and the real robot on a full-size humanoid robot. Extensive experiments and evaluation results verify the effectiveness of our proposed framework.

Xingyu Chen, Qi Zhang, Xiaoyu Li et al.

Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, we introduce an anti-occlusion module to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can hallucinate the desired appearances and render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.

Xun Tan, Xingyu Chen, Guowei Zhang et al.

Point clouds and images could provide complementary information when representing 3D objects. Fusing the two kinds of data usually helps to improve the detection results. However, it is challenging to fuse the two data modalities, due to their different characteristics and the interference from the non-interest areas. To solve this problem, we propose a Multi-Branch Deep Fusion Network (MBDF-Net) for 3D object detection. The proposed detector has two stages. In the first stage, our multi-branch feature extraction network utilizes Adaptive Attention Fusion (AAF) modules to produce cross-modal fusion features from single-modal semantic features. In the second stage, we use a region of interest (RoI) -pooled fusion module to generate enhanced local features for refinement. A novel attention-based hybrid sampling strategy is also proposed for selecting key points in the downsampling process. We evaluate our approach on two widely used benchmark datasets including KITTI and SUN-RGBD. The experimental results demonstrate the advantages of our method over state-of-the-art approaches.

Jie Xu, Xingyu Chen, Xuguang Lan et al.

Human motion prediction is an important and challenging topic that has promising prospects in efficient and safe human-robot-interaction systems. Currently, the majority of the human motion prediction algorithms are based on deterministic models, which may lead to risky decisions for robots. To solve this problem, we propose a probabilistic model for human motion prediction in this paper. The key idea of our approach is to extend the conventional deterministic motion prediction neural network to a Bayesian one. On one hand, our model could generate several future motions when given an observed motion sequence. On the other hand, by calculating the Epistemic Uncertainty and the Heteroscedastic Aleatoric Uncertainty, our model could tell the robot if the observation has been seen before and also give the optimal result among all possible predictions. We extensively validate our approach on a large scale benchmark dataset Human3.6m. The experiments show that our approach performs better than deterministic methods. We further evaluate our approach in a Human-Robot-Interaction (HRI) scenario. The experimental results show that our approach makes the interaction more efficient and safer.

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.

Tao Wang, Ruixin Zhang, Xingyu Chen et al.

Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of accuracy, raising the contradiction between standard and adversarial accuracies. In this paper, we observe an interesting phenomenon that feature statistics change monotonically and smoothly w.r.t the rising of attacking strength. Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength. This is done by predicting a fusing weight in a dual-BN architecture. Unlike previous works that need to either retrain the model or manually tune a hyper-parameters for different attacking strengths, our method can deal with arbitrary attacking strengths with a single model without introducing any hyper-parameter. Importantly, our method improves the model robustness against adversarial samples without incurring much loss in standard accuracy. Experiments on CIFAR-10, SVHN, and tiny-ImageNet datasets demonstrate that our method outperforms the state-of-the-art under a wide range of attacking strengths.

Vítor Albiero, Xingyu Chen, Xi Yin et al.

We propose real-time, six degrees of freedom (6DoF), 3D face pose estimation without face detection or landmark localization. We observe that estimating the 6DoF rigid transformation of a face is a simpler problem than facial landmark detection, often used for 3D face alignment. In addition, 6DoF offers more information than face bounding box labels. We leverage these observations to make multiple contributions: (a) We describe an easily trained, efficient, Faster R-CNN--based model which regresses 6DoF pose for all faces in the photo, without preliminary face detection. (b) We explain how pose is converted and kept consistent between the input photo and arbitrary crops created while training and evaluating our model. (c) Finally, we show how face poses can replace detection bounding box training labels. Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators. Remarkably, our method also surpasses SotA models of comparable complexity on the WIDER FACE detection benchmark, despite not been optimized on bounding box labels.

Junming Ma, Chaofan Yu, Aihui Zhou et al.

We present S3ML, a secure serving system for machine learning inference in this paper. S3ML runs machine learning models in Intel SGX enclaves to protect users' privacy. S3ML designs a secure key management service to construct flexible privacy-preserving server clusters and proposes novel SGX-aware load balancing and scaling methods to satisfy users' Service-Level Objectives. We have implemented S3ML based on Kubernetes as a low-overhead, high-available, and scalable system. We demonstrate the system performance and effectiveness of S3ML through extensive experiments on a series of widely-used models.

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.