Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When dealing with more than two views, a combinatorial number of error prone pairwise reconstructions are usually followed by an expensive global optimization, which often fails to rectify the pairwise reconstruction errors. To handle more views, reduce errors, and improve inference time, we propose the fast single-stage feed-forward network MV- DUSt3R. At its core are multi-view decoder blocks which exchange information across any number of views while considering one reference view. To make our method robust to reference view selection, we further propose MV-DUSt3R+, which employs cross-reference-view blocks to fuse information across different reference view choices. To further enable novel view synthesis, we extend both by adding and jointly training Gaussian splatting heads. Experiments on multi-view stereo reconstruction, multi-view pose estimation, and novel view synthesis confirm that our methods improve significantly upon prior art. Code released.1

Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent interaction and enables embodied agents to perceive and act within real environments with human‑like capabilities. However, existing datasets are often derived from limited simulators or utilize traditional Structure-from-Motion for up-to-scale annotation and offer limited descriptive captioning, which restricts the capacity of foundation models to accurately interpret real-world dynamics from monocular videos, commonly sourced from the internet. To bridge these gaps, we introduce **DynamicVerse**, a physical‑scale, multimodal 4D world modeling framework for dynamic real-world video. We employ large vision, geometric, and multimodal models to interpret metric-scale static geometry, real-world dynamic motion, instance-level masks, and holistic descriptive captions. By integrating window-based Bundle Adjustment with global optimization, our method converts long real-world video sequences into a comprehensive 4D multimodal format. DynamicVerse delivers a large-scale dataset consists of 100K+ videos with 800K+ annotated masks and 10M+ frames from internet videos. Experimental evaluations on three benchmark tasks, namely video depth estimation, camera pose estimation, and camera intrinsics estimation, demonstrate that our 4D modeling achieves superior performance in capturing physical-scale measurements with greater global accuracy than existing methods.

Wheel-legged robots integrate the adaptability of legged locomotion with the efficiency of wheeled movement, enabling agile traversal across diverse terrains. However, abrupt terrain transitions introduce substantial state variations, including velocity fluctuations, posture shifts, and slippage, which pose significant challenges to locomotion stability. To address these issues, we propose a state error compensation framework that integrates a residual network with a trust-region mechanism. The residual network implicitly captures nonlinear contact dynamics, enabling real-time correction of slippage-induced state deviations, while the trust-region mechanism regulates compensation amplitude to maintain stable locomotion. Furthermore, we introduce a dual-source contrastive learning strategy, which explicitly differentiates terrain-induced transitions from external perturbations, facilitating context-aware error recovery. The proposed framework is integrated into a model-free reinforcement learning pipeline, ensuring adaptability to previously unseen environments. To further enhance robustness, an uncertainty-aware calibration module is introduced. This module dynamically adjusts the trust region boundary in real time, leveraging sensory feedback to adaptively constrain residual corrections and prevent over-adjustment, thereby maintaining stability during diverse terrain transitions. Experimental results demonstrate that the proposed framework achieves a 96.7% terrain traversal success rate and 92% velocity tracking accuracy under dynamic disturbances. On unstructured and mixed terrains, it maintains a mean velocity tracking error of 0.15 m/s and stable posture, with pitch and roll angles constrained to ±0.04 rad and ±0.02 rad, respectively.

The techniques for 3D indoor scene capturing are widely used, but the meshes produced leave much to be desired. In this paper, we propose "RoomDreamer", which leverages powerful natural language to synthesize a new room with a different style. Unlike existing image synthesis methods, our work addresses the challenge of synthesizing both geometry and texture aligned to the input scene structure and prompt simultaneously. The key insight is that a scene should be treated as a whole, taking into account both scene texture and geometry. The proposed framework consists of two significant components: Geometry Guided Diffusion and Mesh Optimization. Geometry Guided Diffusion for 3D Scene guarantees the consistency of the scene style by applying the 2D prior to the entire scene simultaneously. Mesh Optimization improves the geometry and texture jointly and eliminates the artifacts in the scanned scene. To validate the proposed method, real indoor scenes scanned with smartphones are used for extensive experiments, through which the effectiveness of our method is demonstrated.

In large-scale online service systems, software changes are inevitable and frequent. Due to importing new code or configurations, changes are likely to incur incidents and destroy user experience. Thus it is essential for engineers to identify bad software changes, so as to reduce the influence of incidents and improve system re- liability. To better understand bad software changes, we perform the first empirical study based on large-scale real-world data from a large commercial bank. Our quantitative analyses indicate that about 50.4% of incidents are caused by bad changes, mainly be- cause of code defect, configuration error, resource contention, and software version. Besides, our qualitative analyses show that the current practice of detecting bad software changes performs not well to handle heterogeneous multi-source data involved in soft- ware changes. Based on the findings and motivation obtained from the empirical study, we propose a novel approach named SCWarn aiming to identify bad changes and produce interpretable alerts accurately and timely. The key idea of SCWarn is drawing support from multimodal learning to identify anomalies from heterogeneous multi-source data. An extensive study on two datasets with various bad software changes demonstrates our approach significantly outperforms all the compared approaches, achieving 0.95 F1-score on average and reducing MTTD (mean time to detect) by 20.4%∼60.7%. In particular, we shared some success stories and lessons learned from the practical usage.

In this article, we propose a novel object detection algorithm named "Deep Regionlets" by integrating deep neural networks and a conventional detection schema for accurate generic object detection. Motivated by the effectiveness of regionlets for modeling object deformations and multiple aspect ratios, we incorporate regionlets into an end-to-end trainable deep learning framework. The deep regionlets framework consists of a region selection network and a deep regionlet learning module. Specifically, given a detection bounding box proposal, the region selection network provides guidance on where to select sub-regions from which features can be learned from. An object proposal typically contains three - 16 sub-regions. The regionlet learning module focuses on local feature selection and transformations to alleviate the effects of appearance variations. To this end, we first realize non-rectangular region selection within the detection framework to accommodate variations in object appearance. Moreover, we design a "gating network" within the regionlet leaning module to enable instance dependent soft feature selection and pooling. The Deep Regionlets framework is trained end-to-end without additional efforts. We present ablation studies and extensive experiments on the PASCAL VOC dataset and the Microsoft COCO dataset. The proposed method yields competitive performance over state-of-the-art algorithms, such as RetinaNet and Mask R-CNN, even without additional segmentation labels.

Due to the shortcomings of the weakly supervised and fully supervised object detection (i.e., unsatisfactory performance and expensive annotations, respectively), leveraging partially labeled images in a cost-effective way to train an object detector has attracted much attention. In this paper, we formulate this challenging task as a missing bounding-boxes' object detection problem. Specifically, we develop a pseudo ground truth mining procedure to automatically find the missing bounding boxes for the unlabeled instances, called pseudo ground truths here, in the training data, and then combine the mined pseudo ground truths and the labeled annotations to train a fully supervised object detector. Furthermore, we propose an incremental learning framework to gradually incorporate the results of the trained fully supervised detector to improve the performance of the missing bounding-boxes' object detection. More importantly, we find an effective way to label the massive images with limited labors and funds, which is crucial when building a large-scale weakly/webly labeled dataset for object detection. The extensive experiments on the PASCAL VOC and COCO benchmarks demonstrate that our proposed method can narrow the gap between the fully supervised and weakly supervised object detectors, and outperform the previous state-of-the-art weakly supervised detectors by a large margin (more than 3% mAP absolutely) when the missing rate equals 0.9. Moreover, our proposed method with 30% missing bounding-box annotations can achieve comparable performance to some fully supervised detectors.

Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful. Despite the great success of the generic object detection methods trained on ground-to-ground images, a huge performance drop is observed when they are directly applied to images captured by UAVs. The unsatisfactory performance is owing to many UAV-specific nuisances, such as varying flying altitudes, adverse weather conditions, dynamically changing viewing angles, etc. Those nuisances constitute a large number of fine-grained domains, across which the detection model has to stay robust. Fortunately, UAVs will record meta-data that depict those varying attributes, which are either freely available along with the UAV images, or can be easily obtained. We propose to utilize those free meta-data in conjunction with associated UAV images to learn domain-robust features via an adversarial training framework dubbed Nuisance Disentangled Feature Transform (NDFT), for the specific challenging problem of object detection in UAV images, achieving a substantial gain in robustness to those nuisances. We demonstrate the effectiveness of our proposed algorithm, by showing state-of-the- art performance (single model) on two existing UAV-based object detection benchmarks. The code is available at https://github.com/TAMU-VITA/UAV-NDFT.

A robust and succinct matrix-based method is developed to simulate the response of eccentered resistivity logging tools in anisotropic geological formations. This is done by first deriving the solution of the state vector describing the potential and the current component along the radial direction in a cylindrical system. Rescaled cylindrical eigenfunctions are employed to overcome the poor scaling inherent to the canonical cylindrical functions for very small or very large arguments. A Levin-type method for approximating integrals with rapidly oscillatory functions is introduced to effectively perform the numerical integrals. The influence of both the translational and rotational eccentricities of the logging tool within the borehole surrounded by an anisotropic formation is studied based on numerical results provided by the present matrix method. We found that neither translational nor rotational eccentricity can be neglected, especially in low-resistive or anisotropic geological formations.

Although deep learning has yielded impressive performance for face recognition, many studies have shown that different networks learn different feature maps: while some networks are more receptive to pose and illumination others appear to capture more local information. Thus, in this work, we propose a deep heterogeneous feature fusion network to exploit the complementary information present in features generated by different deep convolutional neural networks (DCNNs) for template-based face recognition, where a template refers to a set of still face images or video frames from different sources which introduces more blur, pose, illumination and other variations than traditional face datasets. The proposed approach efficiently fuses the discriminative information of different deep features by 1) jointly learning the non-linear high-dimensional projection of the deep features and 2) generating a more discriminative template representation which preserves the inherent geometry of the deep features in the feature space. Experimental results on the IARPA Janus Challenge Set 3 (Janus CS3) dataset demonstrate that the proposed method can effectively improve the recognition performance. In addition, we also present a series of covariate experiments on the face verification task for in-depth qualitative evaluations for the proposed approach.

In this paper, we propose a novel regularized sparse coding approach for template-based unconstrained face verification. Unlike traditional verification tasks, which require the evaluation on image-to-image or video-to-video pairs, template-based face verification/recognition methods can exploit training and/or gallery data containing a mixture of both images or videos from the person of interest. The proposed regularized sparse coding approach addresses the adaptation to training and gallery data using three steps. First, we construct a reference dictionary, which represents the training set. Then we learn the discriminative sparse codes of the templates for verification through the proposed template regularized sparse coding approach. Finally, we measure the similarity between templates. An efficient algorithm is employed to learn the template regularized sparse codes. Extensive experiments on the template-based verification benchmark dataset show that the proposed approach outperforms several state-of-the-art methods.

In this paper, we propose a structured dictionary learning framework for video-based face recognition. We discover the invariant structural information from different videos of each subject. Specifically, we employ dictionary learning and low-rank approximation to preserve the invariant structure of face images in videos. The learned dictionary is both discriminative and reconstructive. Thus, we not only minimize the reconstruction error of all the face images but also encourage a sub-dictionary to represent the corresponding subject from different videos. Moreover, by introducing the low-rank approximation, the proposed method is able to discover invariant structured information from different videos of the same subject. To this end, an efficient alternating algorithm is employed to learn our structured dictionary. Extensive experiments on three video-based face recognition databases show that our approach outperforms several state-of-the-art methods.

Domain adaptation (DA) tackles the problem where data from the training set (source domain) and test set (target domain) have different underlying distributions. For instance, training and testing images may be acquired under different environments, viewpoints and illumination conditions. In this paper, we focus on the more challenging unsupervised DA problem where the samples in the target domain are unlabeled. It is noticed that dictionary learning has gained a lot of popularity due to the fact that images of interest could be reconstructed sparsely in an appropriately learned dictionary [1]. Specifically, we propose a novel domain-adaptive dictionary learning approach to generate a set of intermediate domains which bridge the gap between source and target domains. Our approach defines two types of dictionaries: a common dictionary and a domain-specific dictionary. The overall learning process illustrated in Figure 1 consists of three steps: (1) At the beginning, we first learn the common dictionary DC, domainspecific dictionaries D0 and Dt for source and target domains. (2) At the k-th step, we enforce the recovered feature representations of target data in all available domains to have the same sparse codes, while adapting the most recently obtained dictionary Dk to better represent the target domain. Then we multiply dictionaries in the k-th domain with the corresponding sparse codes to recover feature representations of target data Xk t in this domain. (3) We update Dk to find the next domain-specific dictionary Dk+1 by further minimizing the reconstruction error in representing the target data. Then we alternate between the steps of sparse coding and dictionary updating until the stopping criteria is satisfied. Notations: Let X s ∈ Rd×Ns , X t ∈ Rd×Nt be the feature representations of source and target data respectively, where d is the feature dimension, Ns and Nt are the number of samples in the two domains. The feature representations of recovered source and target data in the k-th intermediate domain are denoted as Xs ∈ Rd×Ns and Xk t ∈ Rd×Nt respectively. The common dictionary is denoted as DC, whereas source-specific and targetspecific dictionaries are denoted as D0, Dt respectively. Similarly, we use Dk,k = 1...N to denote the domain-specific dictionary for the k-th domain, where N is the number of intermediate domains. We set all the dictionaries to be of the same size ∈Rd×n. At the beginning, we learn the common dictionary DC by minimizing the reconstruction error of both source and target data as follows:

A new ARTMAP-based network is proposed, which is in part a generalization of Williamson's Gaussian ARTMAP. The training of the new network is based on activation and match functions that are equal and identical to Mahalanobis distance. The classification treats the clusters obtained through training as Gaussian mixture models. The training process has improved its efficiency due to the fact that the repeated searches for the resonant node have been eliminated. In addition, the inverse covariance matrices are computed recurrently. The new network is analyzed and compared with the fuzzy ARTMAP and Gaussian ARTMAP. The results from the new network have shown much better hit rates at fewer output nodes on several benchmark problems. A complexity analysis of the three networks is also provided.