This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon an improved 3D encoder by extending ReCon to ReCon++ that benefits from multi-view image distillation for enhanced geometry understanding. By utilizing ReCon++ as the 3D point cloud input encoder for LLMs, ShapeLLM is trained on constructed instruction-following data and tested on our newly human-curated evaluation benchmark, 3D MM-Vet. ReCon++ and ShapeLLM achieve state-of-the-art performance in 3D geometry understanding and language-unified 3D interaction tasks, such as embodied visual grounding.
Accurate pedestrian intention prediction (PIP) by Autonomous Vehicles (AVs) is one of the current research challenges in this field. In this article, we introduce PIP-Net, a novel framework designed to predict pedestrian crossing intentions by AVs in real-world urban scenarios. We offer two variants of PIP-Net designed for different camera mounts and setups. Leveraging both kinematic data and spatial features from the driving scene, the proposed model employs a recurrent and temporal attention-based solution, outperforming state-of-the-art performance. To enhance the visual representation of road users and their proximity to the ego vehicle, we introduce a categorical depth feature map, combined with a local motion flow feature, providing rich insights into the scene dynamics. Additionally, we explore the impact of expanding the camera's field of view, from one to three cameras surrounding the ego vehicle, leading to enhancement in the model's contextual perception. Depending on the traffic scenario and road environment, the model excels in predicting pedestrian crossing intentions up to 4 seconds in advance which is a breakthrough in current research studies in pedestrian intention prediction. Finally, for the first time, we present the Urban-PIP dataset, a customised pedestrian intention prediction dataset, with multi-camera annotations in real-world automated driving scenarios.
We propose a new method for cloth digitalization. Deviating from existing methods which learn from data captured under relatively casual settings, we propose to learn from data captured in strictly tested measuring protocols, and find plausible physical parameters of the cloths. However, such data is currently absent, so we first propose a new dataset with accurate cloth measurements. Further, the data size is considerably smaller than the ones in current deep learning, due to the nature of the data capture process. To learn from small data, we propose a new Bayesian differentiable cloth model to estimate the complex material heterogeneity of real cloths. It can provide highly accurate digitalization from very limited data samples. Through exhaustive evaluation and comparison, we show our method is accurate in cloth digitalization, efficient in learning from limited data samples, and general in capturing material variations. Code and data are available https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization
Pedestrian trajectory prediction is the key technology in many applications for providing insights into human behavior and anticipating human future motions. Most existing empirical models are explicitly formulated by observed human behaviors using explicable mathematical terms with a deterministic nature, while recent work has focused on developing hybrid models combined with learning-based techniques for powerful expressiveness while maintaining explainability. However, the deterministic nature of the learned steering behaviors from the empirical models limits the models' practical performance. To address this issue, this work proposes the social conditional variational autoencoder (SocialCVAE) for predicting pedestrian trajectories, which employs a CVAE to explore behavioral uncertainty in human motion decisions. SocialCVAE learns socially reasonable motion randomness by utilizing a socially explainable interaction energy map as the CVAE's condition, which illustrates the future occupancy of each pedestrian's local neighborhood area. The energy map is generated using an energy-based interaction model, which anticipates the energy cost (i.e., repulsion intensity) of pedestrians' interactions with neighbors. Experimental results on two public benchmarks including 25 scenes demonstrate that SocialCVAE significantly improves prediction accuracy compared with the state-of-the-art methods, with up to 16.85% improvement in Average Displacement Error (ADE) and 69.18% improvement in Final Displacement Error (FDE).
Dynamic magnetic resonance imaging (MRI) plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled but the image reconstruction poses a great challenge of high-dimensional processing. This challenge leads to necessitate extensive training data in many deep learning reconstruction methods. This work proposes a novel and efficient approach, leveraging a dimension-reduced separable learning scheme that excels even with highly limited training data. We further integrate it with spatiotemporal priors to develop a Deep Separable Spatiotemporal Learning network (DeepSSL), which unrolls an iteration process of a reconstruction model with both temporal low-rankness and spatial sparsity. Intermediate outputs are visualized to provide insights into the network's behavior and enhance its interpretability. Extensive results on cardiac cine datasets show that the proposed DeepSSL is superior to the state-of-the-art methods visually and quantitatively, while reducing the demand for training cases by up to 75%. And its preliminary adaptability to cardiac patients has been verified through experienced radiologists' and cardiologists' blind reader study. Additionally, DeepSSL also benefits for achieving the downstream task of cardiac segmentation with higher accuracy and shows robustness in prospective real-time cardiac MRI.
Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse weather scenarios encompass multiple possibilities, and high-fidelity data synthesis with controllable weather is under-researched in previous UDA works. The recent strides in large-scale text-to-image diffusion models (DM) have ushered in a novel avenue for research, enabling the generation of realistic images conditioned on semantic labels. This capability proves instrumental for cross-domain data synthesis from source to target domain owing to their shared label space. Thus, source domain labels can be paired with those generated pseudo target data for training UDA. However, from the UDA perspective, there exists several challenges for DM training: (i) ground-truth labels from target domain are missing; (ii) the prompt generator may produce vague or noisy descriptions of images from adverse weathers; (iii) existing arts often struggle to well handle the complex scene structure and geometry of urban scenes when conditioned only on semantic labels. To tackle the above issues, we propose ControlUDA, a diffusion-assisted framework tailored for UDA segmentation under adverse weather conditions. It first leverages target prior from a pre-trained segmentor for tuning the DM, compensating the missing target domain labels; It also contains UDAControlNet, a condition-fused multi-scale and prompt-enhanced network targeted at high-fidelity data generation in adverse weathers. Training UDA with our generated data brings the model performances to a new milestone (72.0 mIoU) on the popular Cityscapes-to-ACDC benchmark for adverse weathers. Furthermore, ControlUDA helps to achieve good model generalizability on unseen data.
Open-vocabulary 3D instance segmentation has emerged as a frontier topic due to its capability to segment 3D instances beyond a predefined set of categories. However, compared to significant progress in the 2D domain, methods for 3D open-vocabulary instance segmentation are hindered by the limited scale of high-quality annotated 3D data. To harness the capabilities of 2D models, recent efforts have focused on merging 2D masks based on metrics such as geometric and semantic similarity to form 3D instances. In contrast to these local metrics, we propose a novel metric called view consensus to better exploit multi-view observation. The key insight is that two 2D masks should be considered as belonging to the same instance if a considerable number of other 2D masks from other views contain both these two masks. Based on this metric, we build a global mask graph and iteratively cluster masks, prioritizing mask pairs with solid view consensus. The corresponding 3D points cluster of these 2D mask clusters can be regarded as 3D instances, along with the fused open-vocabulary features from clustered 2D masks. Through this multi-view verification and fusion mechanism, our method effectively leverages the prior instance knowledge from massive 2D masks predicted by visual foundation models, eliminating the need for training on 3D data. Experiments on publicly available datasets, including ScanNet200 and MatterPort3D, demonstrate that our method achieves state-of-the-art performance in both open-vocabulary instance segmentation and class-agnostic mask generation. Our project page is at https://pku-epic.github.io/MaskClustering.
The emergence of neural networks constrained by physical governing equations has sparked a new trend in deep learning research, which is known as Physics-Informed Neural Networks (PINNs). However, solving high-dimensional problems with PINNs is still a substantial challenge, the space complexity brings difficulty to solving large multidirectional problems. In this paper, a novel PINN framework to quickly predict several three-dimensional Terzaghi consolidation cases under different conditions is proposed. Meanwhile, the loss functions for different cases are introduced, and their differences in three-dimensional consolidation problems are highlighted. The tuning strategies for the PINNs framework for three-dimensional consolidation problems are introduced. Then, the performance of PINNs is tested and compared with traditional numerical methods adopted in forward problems, and the coefficients of consolidation and the impact of noisy data in inverse problems are identified. Finally, the results are summarized and presented from three-dimensional simulations of PINNs, which show an accuracy rate of over 99% compared with ground truth for both forward and inverse problems. These results are desirable with good accuracy and can be used for soil settlement prediction, which demonstrates that the proposed PINNs framework can learn the three-dimensional consolidation PDE well. Keywords: Three-dimensional Terzaghi consolidation; Physics-informed neural networks (PINNs); Forward problems; Inverse problems; soil settlement
This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts different extraction strategies based on the audio quality, striking a balance between interference removal and speech preservation, which benifits the back-end automatic speech recognition (ASR) systems. Experiments show that our approach achieves a character error rate (CER) of 24.2% and 33.2% on the Dev and Eval set, respectively, obtaining the second place in the challenge.