Xiaohan Zhang

Zhuoyi Yang, Jiayan Teng, Wendi Zheng et al. · tsinghua

We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels. Previous video generation models often had limited movement and short durations, and is difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we propose a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions, to improve both compression rate and video fidelity. Second, to improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing a progressive training and multi-resolution frame pack technique, CogVideoX is adept at producing coherent, long-duration, different shape videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method, greatly contributing to the generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of both 3D Causal VAE, Video caption model and CogVideoX are publicly available at https://github.com/THUDM/CogVideo.

Xiaohan Zhang, Bharat Lal Bhatnagar, Vladimir Guzov et al.

Humans interact with an object in many different ways by making contact at different locations, creating a highly complex motion space that can be difficult to learn, particularly when synthesizing such human interactions in a controllable manner. Existing works on synthesizing human scene interaction focus on the high-level control of action but do not consider the fine-grained control of motion. In this work, we study the problem of synthesizing scene interactions conditioned on different contact positions on the object. As a testbed to investigate this new problem, we focus on human-chair interaction as one of the most common actions which exhibit large variability in terms of contacts. We propose a novel synthesis framework COUCH that plans ahead the motion by predicting contact-aware control signals of the hands, which are then used to synthesize contact-conditioned interactions. Furthermore, we contribute a large human-chair interaction dataset with clean annotations, the COUCH Dataset. Our method shows significant quantitative and qualitative improvements over existing methods for human-object interactions. More importantly, our method enables control of the motion through user-specified or automatically predicted contacts.

Xiaohan Zhang, Xingyu Li, Waqas Sultani et al.

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and different capturing time between two views. Despite these difficulties, recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks, in which the training and testing data are captured from two different regions. We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set. In this paper, we propose GeoDTR which explicitly disentangles geometric information from raw features and learns the spatial correlations among visual features from aerial and ground pairs with a novel geometric layout extractor module. This module generates a set of geometric layout descriptors, modulating the raw features and producing high-quality latent representations. In addition, we elaborate on two categories of data augmentations, (i) Layout simulation, which varies the spatial configuration while keeping the low-level details intact. (ii) Semantic augmentation, which alters the low-level details and encourages the model to capture spatial configurations. These augmentations help to improve the performance of the cross-view geo-localization models, especially on the cross-area benchmarks. Moreover, we propose a counterfactual-based learning process to benefit the geometric layout extractor in exploring spatial information. Extensive experiments show that GeoDTR not only achieves state-of-the-art results but also significantly boosts the performance on same-area and cross-area benchmarks.

Xiaohan Zhang, Waqas Sultani, Safwan Wshah

Cross-view geo-localization aims to estimate the GPS location of a query ground-view image by matching it to images from a reference database of geo-tagged aerial images. To address this challenging problem, recent approaches use panoramic ground-view images to increase the range of visibility. Although appealing, panoramic images are not readily available compared to the videos of limited Field-Of-View (FOV) images. In this paper, we present the first cross-view geo-localization method that works on a sequence of limited FOV images. Our model is trained end-to-end to capture the temporal structure that lies within the frames using the attention-based temporal feature aggregation module. To robustly tackle different sequences length and GPS noises during inference, we propose to use a sequential dropout scheme to simulate variant length sequences. To evaluate the proposed approach in realistic settings, we present a new large-scale dataset containing ground-view sequences along with the corresponding aerial-view images. Extensive experiments and comparisons demonstrate the superiority of the proposed approach compared to several competitive baselines.

Xiaohan Zhang, Xingyu Li, Waqas Sultani et al.

Cross-View Geo-Localization (CVGL) estimates the location of a ground image by matching it to a geo-tagged aerial image in a database. Recent works achieve outstanding progress on CVGL benchmarks. However, existing methods still suffer from poor performance in cross-area evaluation, in which the training and testing data are captured from completely distinct areas. We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models' overfitting to low-level details. Our preliminary work introduced a Geometric Layout Extractor (GLE) to capture the geometric layout from input features. However, the previous GLE does not fully exploit information in the input feature. In this work, we propose GeoDTR+ with an enhanced GLE module that better models the correlations among visual features. To fully explore the LS techniques from our preliminary work, we further propose Contrastive Hard Samples Generation (CHSG) to facilitate model training. Extensive experiments show that GeoDTR+ achieves state-of-the-art (SOTA) results in cross-area evaluation on CVUSA, CVACT, and VIGOR by a large margin ($16.44\%$, $22.71\%$, and $13.66\%$ without polar transformation) while keeping the same-area performance comparable to existing SOTA. Moreover, we provide detailed analyses of GeoDTR+. Our code will be available at https://gitlab.com/vail-uvm/geodtr plus.

Ahmad Arrabi, Xiaohan Zhang, Waqas Sultani et al.

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibility. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird's Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multi-modal cross-view dataset, namely VIGORv2 which is built upon VIGOR with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and data will be publicly available.

Xiaohan Zhang, Tavis Shore, Chen Chen et al.

In this paper, we present a high-performing solution to the UAVM 2025 Challenge, which focuses on matching narrow FOV street-level images to corresponding satellite imagery using the University-1652 dataset. As panoramic Cross-View Geo-Localisation nears peak performance, it becomes increasingly important to explore more practical problem formulations. Real-world scenarios rarely offer panoramic street-level queries; instead, queries typically consist of limited-FOV images captured with unknown camera parameters. Our work prioritises discovering the highest achievable performance under these constraints, pushing the limits of existing architectures. Our method begins by retrieving candidate satellite image embeddings for a given query, followed by a re-ranking stage that selectively enhances retrieval accuracy within the top candidates. This two-stage approach enables more precise matching, even under the significant viewpoint and scale variations inherent in the task. Through experimentation, we demonstrate that our approach achieves competitive results -specifically attaining R@1 and R@10 retrieval rates of \topone\% and \topten\% respectively. This underscores the potential of optimised retrieval and re-ranking strategies in advancing practical geo-localisation performance. Code is available at https://github.com/tavisshore/VICI.

Xiaohan Zhang, Zhenyu Sun, Yukui Qiu et al.

Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory. This paper presents a Toy-GS method for accurately rendering large-scale free camera trajectories. Specifically, we propose an adaptive spatial division approach for free trajectories to divide cameras and the sparse point cloud of the entire scene into various regions according to camera poses. Training each local Gaussian in parallel for each area enables us to concentrate on texture details and minimize GPU memory usage. Next, we use the multi-view constraint and position-aware point adaptive control (PPAC) to improve the rendering quality of texture details. In addition, our regional fusion approach combines local and global Gaussians to enhance rendering quality with an increasing number of divided areas. Extensive experiments have been carried out to confirm the effectiveness and efficiency of Toy-GS, leading to state-of-the-art results on two public large-scale datasets as well as our SCUTic dataset. Our proposal demonstrates an enhancement of 1.19 dB in PSNR and conserves 7 G of GPU memory when compared to various benchmarks.

Xiaohan Zhang, Sitong Wang, Yushen Yan et al.

High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision. Existing methods typically partition large scenes into multiple regions, reconstruct a 3D representation using Gaussian splatting for each region, and eventually merge them for novel view rendering. They can accurately render specific scenes, yet they do not generalize effectively for two reasons: (1) rigid spatial partition techniques struggle with arbitrary camera trajectories, and (2) the merging of regions results in Gaussian overlap to distort texture details. To address these challenges, we propose TraGraph-GS, leveraging a trajectory graph to enable high-precision rendering for arbitrarily large-scale scenes. We present a spatial partitioning method for large-scale scenes based on graphs, which incorporates a regularization constraint to enhance the rendering of textures and distant objects, as well as a progressive rendering strategy to mitigate artifacts caused by Gaussian overlap. Experimental results demonstrate its superior performance both on four aerial and four ground datasets and highlight its remarkable efficiency: our method achieves an average improvement of 1.86 dB in PSNR on aerial datasets and 1.62 dB on ground datasets compared to state-of-the-art approaches.

Jingfeng Guo, Xiaohan Zhang, Baozhu Zhao et al.

Existing neural radiance fields (NeRF)-based novel view synthesis methods for large-scale outdoor scenes are mainly built on a single altitude. Moreover, they often require a priori camera shooting height and scene scope, leading to inefficient and impractical applications when camera altitude changes. In this work, we propose an end-to-end framework, termed AG-NeRF, and seek to reduce the training cost of building good reconstructions by synthesizing free-viewpoint images based on varying altitudes of scenes. Specifically, to tackle the detail variation problem from low altitude (drone-level) to high altitude (satellite-level), a source image selection method and an attention-based feature fusion approach are developed to extract and fuse the most relevant features of target view from multi-height images for high-fidelity rendering. Extensive experiments demonstrate that AG-NeRF achieves SOTA performance on 56 Leonard and Transamerica benchmarks and only requires a half hour of training time to reach the competitive PSNR as compared to the latest BungeeNeRF.

Xiaohan Zhang, Yifeng Zhu, Yan Ding et al.

Task and motion planning (TAMP) algorithms aim to help robots achieve task-level goals, while maintaining motion-level feasibility. This paper focuses on TAMP domains that involve robot behaviors that take extended periods of time (e.g., long-distance navigation). In this paper, we develop a visual grounding approach to help robots probabilistically evaluate action feasibility, and introduce a TAMP algorithm, called GROP, that optimizes both feasibility and efficiency. We have collected a dataset that includes 96,000 simulated trials of a robot conducting mobile manipulation tasks, and then used the dataset to learn to ground symbolic spatial relationships for action feasibility evaluation. Compared with competitive TAMP baselines, GROP exhibited a higher task-completion rate while maintaining lower or comparable action costs. In addition to these extensive experiments in simulation, GROP is fully implemented and tested on a real robot system.

Yan Ding, Xiaohan Zhang, Xingyue Zhan et al.

Task and motion planning (TAMP) algorithms have been developed to help robots plan behaviors in discrete and continuous spaces. Robots face complex real-world scenarios, where it is hardly possible to model all objects or their physical properties for robot planning (e.g., in kitchens or shopping centers). In this paper, we define a new object-centric TAMP problem, where the TAMP robot does not know object properties (e.g., size and weight of blocks). We then introduce Task-Motion Object-Centric planning ({\bf TMOC}), a grounded TAMP algorithm that learns to ground objects and their physical properties with a physics engine. TMOC is particularly useful for those tasks that involve dynamic complex robot-multi-object interactions that can hardly be modeled beforehand. We have demonstrated and evaluated TMOC in simulation and using a real robot. Results show that TMOC outperforms competitive baselines from the literature in cumulative utility.

Daniel Wilson, Xiaohan Zhang, Waqas Sultani et al.

The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates. The entity of interest may be an image, sequence of images, a video, satellite image, or even objects visible within the image. As massive datasets of GPS tagged media have rapidly become available due to smartphones and the internet, and deep learning has risen to enhance the performance capabilities of machine learning models, the fields of visual and object geo-localization have emerged due to its significant impact on a wide range of applications such as augmented reality, robotics, self-driving vehicles, road maintenance, and 3D reconstruction. This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization). We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.

Daniel Wilson, Thayer Alshaabi, Colin Van Oort et al.

Geo-localizing static objects from street images is challenging but also very important for road asset mapping and autonomous driving. In this paper we present a two-stage framework that detects and geolocalizes traffic signs from low frame rate street videos. Our proposed system uses a modified version of RetinaNet (GPS-RetinaNet), which predicts a positional offset for each sign relative to the camera, in addition to performing the standard classification and bounding box regression. Candidate sign detections from GPS-RetinaNet are condensed into geolocalized signs by our custom tracker, which consists of a learned metric network and a variant of the Hungarian Algorithm. Our metric network estimates the similarity between pairs of detections, then the Hungarian Algorithm matches detections across images using the similarity scores provided by the metric network. Our models were trained using an updated version of the ARTS dataset, which contains 25,544 images and 47.589 sign annotations ~\cite{arts}. The proposed dataset covers a diverse set of environments gathered from a broad selection of roads. Each annotaiton contains a sign class label, its geospatial location, an assembly label, a side of road indicator, and unique identifiers that aid in the evaluation. This dataset will support future progress in the field, and the proposed system demonstrates how to take advantage of some of the unique characteristics of a realistic geolocalization dataset.

Zhuoran Yu, Aojun Zhou, Yukun Ma et al.

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that trivially evaluating low-resolution images on networks trained with high-resolution images results in a catastrophic accuracy drop in standard CNN architectures. We propose a novel training regime called Scale calibrated Training(SCT) which allows networks to learn from various scales of input simultaneously. By taking advantages of SCT, single network can provide decent accuracy at test time in response to multiple test scales. In our analysis, we surprisingly find that vanilla batch normalization can lead to sub-optimal performance in SCT. Therefore, a novel normalization scheme called Scale-Specific Batch Normalization is equipped to SCT in replacement of batch normalization. Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1.7% and 11.5% accuracy when testing on image sizes of 224 and 128 respectively.