Shan Wang

Tianyu Yu, Jinyi Hu, Yuan Yao et al. · tsinghua

Recent Multimodal Large Language Models (MLLMs) exhibit impressive abilities to perceive images and follow open-ended instructions. The capabilities of MLLMs depend on two crucial factors: the model architecture to facilitate the feature alignment of visual modules and large language models; the multimodal instruction tuning datasets for human instruction following. (i) For the model architecture, most existing models introduce an external bridge module to connect vision encoders with language models, which needs an additional feature-alignment pre-training. In this work, we discover that compact pre-trained vision language models can inherently serve as ``out-of-the-box'' bridges between vision and language. Based on this, we propose Muffin framework, which directly employs pre-trained vision-language models to act as providers of visual signals. (ii) For the multimodal instruction tuning datasets, existing methods omit the complementary relationship between different datasets and simply mix datasets from different tasks. Instead, we propose UniMM-Chat dataset which explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions. We merge information describing the same image from diverse datasets and transforms it into more knowledge-intensive conversation data. Experimental results demonstrate the effectiveness of the Muffin framework and UniMM-Chat dataset. Muffin achieves state-of-the-art performance on a wide range of vision-language tasks, significantly surpassing state-of-the-art models like LLaVA and InstructBLIP. Our model and dataset are all accessible at https://github.com/thunlp/muffin.

Jiawei Liu, Changkun Ye, Shan Wang et al.

For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary classification models are prone to being over-confident. To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image. ASLP employs our proposed Self-Calibrating Binary Cross Entropy (SC-BCE) loss, which unifies label perturbation processes including stochastic approaches (like DisturbLabel), and label smoothing, to correct calibration while maintaining classification rates. ASLP follows Maximum Entropy Inference of classic statistical mechanics to maximise prediction entropy with respect to missing information. It performs this while: (1) preserving classification accuracy on known data as a conservative solution, or (2) specifically improves model calibration degree by minimising the gap between the prediction accuracy and expected confidence of the target training label. Extensive results demonstrate that ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data. The code is available on https://github.com/Carlisle-Liu/ASLP.

Shan Wang, Yanhao Zhang, Ankit Vora et al.

Existing spatial localization techniques for autonomous vehicles mostly use a pre-built 3D-HD map, often constructed using a survey-grade 3D mapping vehicle, which is not only expensive but also laborious. This paper shows that by using an off-the-shelf high-definition satellite image as a ready-to-use map, we are able to achieve cross-view vehicle localization up to a satisfactory accuracy, providing a cheaper and more practical way for localization. While the utilization of satellite imagery for cross-view localization is an established concept, the conventional methodology focuses primarily on image retrieval. This paper introduces a novel approach to cross-view localization that departs from the conventional image retrieval method. Specifically, our method develops (1) a Geometric-align Feature Extractor (GaFE) that leverages measured 3D points to bridge the geometric gap between ground and overhead views, (2) a Pose Aware Branch (PAB) adopting a triplet loss to encourage pose-aware feature extraction, and (3) a Recursive Pose Refine Branch (RPRB) using the Levenberg-Marquardt (LM) algorithm to align the initial pose towards the true vehicle pose iteratively. Our method is validated on KITTI and Ford Multi-AV Seasonal datasets as ground view and Google Maps as the satellite view. The results demonstrate the superiority of our method in cross-view localization with median spatial and angular errors within $1$ meter and $1^\circ$, respectively.

Shan Wang, Yanhao Zhang, Akhil Perincherry et al.

This paper proposes a fine-grained self-localization method for outdoor robotics that utilizes a flexible number of onboard cameras and readily accessible satellite images. The proposed method addresses limitations in existing cross-view localization methods that struggle to handle noise sources such as moving objects and seasonal variations. It is the first sparse visual-only method that enhances perception in dynamic environments by detecting view-consistent key points and their corresponding deep features from ground and satellite views, while removing off-the-ground objects and establishing homography transformation between the two views. Moreover, the proposed method incorporates a spatial embedding approach that leverages camera intrinsic and extrinsic information to reduce the ambiguity of purely visual matching, leading to improved feature matching and overall pose estimation accuracy. The method exhibits strong generalization and is robust to environmental changes, requiring only geo-poses as ground truth. Extensive experiments on the KITTI and Ford Multi-AV Seasonal datasets demonstrate that our proposed method outperforms existing state-of-the-art methods, achieving median spatial accuracy errors below $0.5$ meters along the lateral and longitudinal directions, and a median orientation accuracy error below 2 degrees.

Yujiao Shi, Xin Yu, Shan Wang et al.

This paper tackles the problem of Cross-view Video-based camera Localization (CVL). The task is to localize a query camera by leveraging information from its past observations, i.e., a continuous sequence of images observed at previous time stamps, and matching them to a large overhead-view satellite image. The critical challenge of this task is to learn a powerful global feature descriptor for the sequential ground-view images while considering its domain alignment with reference satellite images. For this purpose, we introduce CVLNet, which first projects the sequential ground-view images into an overhead view by exploring the ground-and-overhead geometric correspondences and then leverages the photo consistency among the projected images to form a global representation. In this way, the cross-view domain differences are bridged. Since the reference satellite images are usually pre-cropped and regularly sampled, there is always a misalignment between the query camera location and its matching satellite image center. Motivated by this, we propose estimating the query camera's relative displacement to a satellite image before similarity matching. In this displacement estimation process, we also consider the uncertainty of the camera location. For example, a camera is unlikely to be on top of trees. To evaluate the performance of the proposed method, we collect satellite images from Google Map for the KITTI dataset and construct a new cross-view video-based localization benchmark dataset, KITTI-CVL. Extensive experiments have demonstrated the effectiveness of video-based localization over single image-based localization and the superiority of each proposed module over other alternatives.

Hanlin Wu, Ning Ni, Shan Wang et al.

Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only consider a single and fixed degradation (such as bicubic interpolation) and cannot flexibly handle complex degradations in real scenes. Therefore, designing a super-resolution (SR) model that can cope with various degradations is gradually attracting the attention of researchers. Some studies first estimate the degradation kernels and then perform degradation-adaptive SR but face the problems of estimation error amplification and insufficient high-frequency details in the results. Although blind SR algorithms based on generative adversarial networks (GAN) have greatly improved visual quality, they still suffer from pseudo-texture, mode collapse, and poor training stability. In this article, we propose a novel blind SR framework based on the stochastic normalizing flow (BlindSRSNF) to address the above problems. BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood. BlindSRSNF is easy to train and can generate photo-realistic SR results that outperform GAN-based models. Besides, we introduce a degradation representation strategy based on contrastive learning to avoid the error amplification problem caused by the explicit degradation estimation. Comprehensive experiments show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.

Shan Wang, Peixia Li, Chenchen Xu et al.

We propose Light-Geometry Interaction (LGI) maps, a novel representation that encodes light-aware occlusion from monocular depth. Unlike ray tracing, which requires full 3D reconstruction, LGI captures essential light-shadow interactions reliably and accurately, computed from off-the-shelf 2.5D depth map predictions. LGI explicitly ties illumination direction to geometry, providing a physics-inspired prior that constrains generative models. Without such prior, these models often produce floating shadows, inconsistent illumination, and implausible shadow geometry. Building on this representation, we propose a unified pipeline for joint shadow generation and relighting - unlike prior methods that treat them as disjoint tasks - capturing the intrinsic coupling of illumination and shadowing essential for modeling indirect effects. By embedding LGI into a bridge-matching generative backbone, we reduce ambiguity and enforce physically consistent light-shadow reasoning. To enable effective training, we curated the first large-scale benchmark dataset for joint shadow and relighting, covering reflections, transparency, and complex interreflections. Experiments show significant gains in realism and consistency across synthetic and real images. LGI thus bridges geometry-inspired rendering with generative modeling, enabling efficient, physically consistent shadow generation and relighting.

Jiahao Ma, Jinguang Tong, Shan Wang et al.

Multi-view detection incorporates multiple camera views to alleviate occlusion in crowded scenes, where the state-of-the-art approaches adopt homography transformations to project multi-view features to the ground plane. However, we find that these 2D transformations do not take into account the object's height, and with this neglection features along the vertical direction of same object are likely not projected onto the same ground plane point, leading to impure ground-plane features. To solve this problem, we propose VFA, voxelized 3D feature aggregation, for feature transformation and aggregation in multi-view detection. Specifically, we voxelize the 3D space, project the voxels onto each camera view, and associate 2D features with these projected voxels. This allows us to identify and then aggregate 2D features along the same vertical line, alleviating projection distortions to a large extent. Additionally, because different kinds of objects (human vs. cattle) have different shapes on the ground plane, we introduce the oriented Gaussian encoding to match such shapes, leading to increased accuracy and efficiency. We perform experiments on multiview 2D detection and multiview 3D detection problems. Results on four datasets (including a newly introduced MultiviewC dataset) show that our system is very competitive compared with the state-of-the-art approaches. %Our code and data will be open-sourced.Code and MultiviewC are released at https://github.com/Robert-Mar/VFA.

Shan Wang, Chuong Nguyen, Jiawei Liu et al.

Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and (2) highly structured with low intra-class shape variance and overall high appearance consistency. To solve these issues, we propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings. To reduce computational complexity, a novel surface normal estimator is proposed to establish spatial correspondences between the sampled frames, allowing the HomoFusion module to perform a pixel-to-pixel attention mechanism in updating the representation of the occluded road lines or markings. Experiments on ApolloScape, a large-scale lane mark segmentation dataset, and ApolloScape Night with artificial simulated night-time road conditions, demonstrate that our method outperforms other existing SOTA lane mark segmentation models with less than 9\% of their parameters and computational complexity. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy. We also prove the versatility of our HomoFusion approach by applying it to the problem of water puddle segmentation and achieving SOTA performance.