A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects

Multi-sensor fusion perception (MSFP) is a key technology for embodied AI, which can serve a variety of downstream tasks (e.g., 3D object detection and semantic segmentation) and application scenarios (e.g., autonomous driving and swarm robotics). Recently, impressive achievements on AI-based MSFP methods have been reviewed in relevant surveys. However, we observe that the existing surveys have some limitations after a rigorous and detailed investigation. For one thing, most surveys are oriented to a single task or research field, such as 3D object detection or autonomous driving. Therefore, researchers in other related tasks often find it difficult to benefit directly. For another, most surveys only introduce MSFP from a single perspective of multi-modal fusion, while lacking consideration of the diversity of MSFP methods, such as multi-view fusion and time-series fusion. To this end, in this paper, we hope to organize MSFP research from a task-agnostic perspective, where methods are reported from various technical views. Specifically, we first introduce the background of MSFP. Next, we review multi-modal and multi-agent fusion methods. A step further, time-series fusion methods are analyzed. In the era of LLM, we also investigate multimodal LLM fusion methods. Finally, we discuss open challenges and future directions for MSFP. We hope this survey can help researchers understand the important progress in MSFP and provide possible insights for future research.

NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces

This paper reports on the NTIRE 2025 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restoration and Enhancement (NTIRE) workshop at CVPR 2025. This challenge aims to advance the research on depth estimation, specifically to address two of the main open issues in the field: high-resolution and non-Lambertian surfaces. The challenge proposes two tracks on stereo and single-image depth estimation, attracting about 177 registered participants. In the final testing stage, 4 and 4 participating teams submitted their models and fact sheets for the two tracks.

MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining

We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a test-difficulty-driven code-reward scheme to alleviate sparse-reward issues and employing strategic data resampling to stabilize training. Extensive evaluations show that MiMo-7B-Base possesses exceptional reasoning potential, outperforming even much larger 32B models. The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini. The model checkpoints are available at https://github.com/xiaomimimo/MiMo.

LMS-Net: A Learned Mumford-Shah Network For Few-Shot Medical Image Segmentation

Few-shot semantic segmentation (FSS) methods have shown great promise in handling data-scarce scenarios, particularly in medical image segmentation tasks. However, most existing FSS architectures lack sufficient interpretability and fail to fully incorporate the underlying physical structures of semantic regions. To address these issues, in this paper, we propose a novel deep unfolding network, called the Learned Mumford-Shah Network (LMS-Net), for the FSS task. Specifically, motivated by the effectiveness of pixel-to-prototype comparison in prototypical FSS methods and the capability of deep priors to model complex spatial structures, we leverage our learned Mumford-Shah model (LMS model) as a mathematical foundation to integrate these insights into a unified framework. By reformulating the LMS model into prototype update and mask update tasks, we propose an alternating optimization algorithm to solve it efficiently. Further, the iterative steps of this algorithm are unfolded into corresponding network modules, resulting in LMS-Net with clear interpretability. Comprehensive experiments on three publicly available medical segmentation datasets verify the effectiveness of our method, demonstrating superior accuracy and robustness in handling complex structures and adapting to challenging segmentation scenarios. These results highlight the potential of LMS-Net to advance FSS in medical imaging applications. Our code will be available at: https://github.com/SDZhang01/LMSNet

Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction

Magnetic Resonance Imaging (MRI) is widely used in clinical practice, but suffered from prolonged acquisition time. Although deep learning methods have been proposed to accelerate acquisition and demonstrate promising performance, they rely on high-quality fully-sampled datasets for training in a supervised manner. However, such datasets are time-consuming and expensive-to-collect, which constrains their broader applications. On the other hand, self-supervised methods offer an alternative by enabling learning from under-sampled data alone, but most existing methods rely on further partitioned under-sampled k-space data as model's input for training, resulting in a loss of valuable information. Additionally, their models have not fully incorporated image priors, leading to degraded reconstruction performance. In this paper, we propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues when only under-sampled datasets are available. Specifically, by incorporating re-visible dual-domain loss, all under-sampled k-space data are utilized during training to mitigate information loss caused by further partitioning. This design enables the model to implicitly adapt to all under-sampled k-space data as input. Additionally, we design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction, incorporating imaging physics and image priors to guide the reconstruction process. By employing a Spatial-Frequency Feature Extraction (SFFE) block to capture global and local feature representation, we enhance the model's efficiency to learn comprehensive image priors. Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.

Technical Report: Towards Spatial Feature Regularization in Deep-Learning-Based Array-SAR Reconstruction

Array synthetic aperture radar (Array-SAR), also known as tomographic SAR (TomoSAR), has demonstrated significant potential for high-quality 3D mapping, particularly in urban areas.While deep learning (DL) methods have recently shown strengths in reconstruction, most studies rely on pixel-by-pixel reconstruction, neglecting spatial features like building structures, leading to artifacts such as holes and fragmented edges. Spatial feature regularization, effective in traditional methods, remains underexplored in DL-based approaches. Our study integrates spatial feature regularization into DL-based Array-SAR reconstruction, addressing key questions: What spatial features are relevant in urban-area mapping? How can these features be effectively described, modeled, regularized, and incorporated into DL networks? The study comprises five phases: spatial feature description and modeling, regularization, feature-enhanced network design, evaluation, and discussions. Sharp edges and geometric shapes in urban scenes are analyzed as key features. An intra-slice and inter-slice strategy is proposed, using 2D slices as reconstruction units and fusing them into 3D scenes through parallel and serial fusion. Two computational frameworks-iterative reconstruction with enhancement and light reconstruction with enhancement-are designed, incorporating spatial feature modules into DL networks, leading to four specialized reconstruction networks. Using our urban building simulation dataset and two public datasets, six tests evaluate close-point resolution, structural integrity, and robustness in urban scenarios. Results show that spatial feature regularization significantly improves reconstruction accuracy, retrieves more complete building structures, and enhances robustness by reducing noise and outliers.

Promptable Representation Distribution Learning and Data Augmentation for Gigapixel Histopathology WSI Analysis

Gigapixel image analysis, particularly for whole slide images (WSIs), often relies on multiple instance learning (MIL). Under the paradigm of MIL, patch image representations are extracted and then fixed during the training of the MIL classifiers for efficiency consideration. However, the invariance of representations makes it difficult to perform data augmentation for WSI-level model training, which significantly limits the performance of the downstream WSI analysis. The current data augmentation methods for gigapixel images either introduce additional computational costs or result in a loss of semantic information, which is hard to meet the requirements for efficiency and stability needed for WSI model training. In this paper, we propose a Promptable Representation Distribution Learning framework (PRDL) for both patch-level representation learning and WSI-level data augmentation. Meanwhile, we explore the use of prompts to guide data augmentation in feature space, which achieves promptable data augmentation for training robust WSI-level models. The experimental results have demonstrated that the proposed method stably outperforms state-of-the-art methods.

Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis

The development of computational pathology lies in the consensus that pathological characteristics of tumors are significant guidance for cancer diagnostics. Most existing research focuses on the inner-contextual information within each WSI yet ignores the possible inter-correlations between slides. As the development of tumors is a continuous process involving a series of histological, morphological, and genetic changes that accumulate over time, the similarities and differences between WSIs across various stages, grades, locations and patients should potentially contribute to the representation of WSIs and deserve to be taken into account in WSI modeling. To verify the advancement of introducing the slide inter-correlations into the representation learning of WSIs, we proposed a generic WSI analysis pipeline SlideGCD that can be adapted to any existing Multiple Instance Learning (MIL) frameworks and improve their performance. With the new paradigm, the prior knowledge of cancer development can participate in the end-to-end workflow, which concurrently initializes and refines the slide representation, as a guide for message passing in the slide-based graph. Extensive comparisons and experiments are conducted to validate the effectiveness and robustness of the proposed pipeline across 4 different tasks, including cancer subtyping, cancer staging, survival prediction, and gene mutation prediction, with 7 representative SOTA WSI analysis frameworks as backbones.

HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution

Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature distillation is an effective way to enhance performance. However, we find that using residual connections after each block increases the model's storage and computational cost. Therefore, to simplify the network structure and learn higher-level features and relationships between features, we use depthwise separable convolutions, fully connected layers, and activation functions as the basic feature extraction modules. This significantly reduces computational load and the number of parameters while maintaining strong feature extraction capabilities. To further enhance model performance, we propose the Hybrid Attention Separable Block (HASB), which combines channel attention and spatial attention, thus making use of their complementary advantages. Additionally, we use depthwise separable convolutions instead of standard convolutions, significantly reducing the computational load and the number of parameters while maintaining strong feature extraction capabilities. During the training phase, we also adopt a warm-start retraining strategy to exploit the potential of the model further. Extensive experiments demonstrate the effectiveness of our approach. Our method achieves a smaller model size and reduced computational complexity without compromising performance. Code can be available at https://github.com/nathan66666/HASN.git

EHC-MM: Embodied Holistic Control for Mobile Manipulation

Mobile manipulation typically entails the base for mobility, the arm for accurate manipulation, and the camera for perception. It is necessary to follow the principle of Distant Mobility, Close Grasping(DMCG) in holistic control. We propose Embodied Holistic Control for Mobile Manipulation(EHC-MM) with the embodied function of sig(w): By formulating the DMCG principle as a Quadratic Programming (QP) problem, sig(w) dynamically balances the robot's emphasis between movement and manipulation with the consideration of the robot's state and environment. In addition, we propose the Monitor-Position-Based Servoing (MPBS) with sig(w), enabling the tracking of the target during the operation. This approach allows coordinated control between the robot's base, arm, and camera. Through extensive simulations and real-world experiments, our approach significantly improves both the success rate and efficiency of mobile manipulation tasks, achieving a 95.6% success rate in the real-world scenarios and a 52.8% increase in time efficiency.