Yifei Shi

Hui Tian, Chenyang Zhu, Yifei Shi et al.

Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient training and a novel regularization for robustness to sparse sampling. The core idea of SuperUDF draws inspiration from the classical surface approximation operator of locally optimal projection (LOP). The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF. Based on that, a number of inductive biases on UDF geometry and a pre-learned geometry prior are devised to learn UDF estimation efficiently. A novel regularization loss is proposed to make SuperUDF robust to sparse sampling. Furthermore, we also contribute a learning-based mesh extraction from the estimated UDFs. Extensive evaluations demonstrate that SuperUDF outperforms the state of the arts on several public datasets in terms of both quality and efficiency. Code url is https://github.com/THHHomas/SuperUDF.

Yifei Shi, Junhua Xi, Dewen Hu et al.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

Boyan Wan, Yifei Shi, Kai Xu

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a category containing significant intra-category shape variations. This is because the object coordinates induced by global and rigid alignment of objects are semantically incoherent, making the coordinate regression hard to learn and generalize. We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-and-aligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence. SOCS is semantically coherent: Any point on the surface of a object can be mapped to a semantically meaningful location in SOCS, allowing for accurate pose and size estimation under large shape variations. To learn effective coordinate regression to SOCS, we propose a novel multi-scale coordinate-based attention network. Evaluations demonstrate that our method is easy to train, well-generalizing for large intra-category shape variations and robust to inter-object occlusions.

Junhua Xi, Yifei Shi, Yijie Wang et al.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We also devise a multi-task learning for better optimization convergence and depth accuracy. Our method ranks top on both the DTU and the Tanks \& Temples datasets over all previous learning-based methods, achieving overall reconstruction score of 0.33mm on DTU and f-score of 59.48% on Tanks & Temples.

Chuanqing Tang, Yifei Shi, Guanghao Lin et al.

Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In this paper, we tackle a particularly challenging class imbalance problem in multi-view scenarios: long-tailed classification. We propose TMLC, a Trusted Multi-view Long-tailed Classification framework, which makes contributions on two critical aspects: opinion aggregation and pseudo-data generation. Specifically, inspired by Social Identity Theory, we design a group consensus opinion aggregation mechanism that guides decision making toward the direction favored by the majority of the group. In terms of pseudo-data generation, we introduce a novel distance metric to adapt SMOTE for multi-view scenarios and develop an uncertainty-guided data generation module that produces high-quality pseudo-data, effectively mitigating the adverse effects of class imbalance. Extensive experiments on long-tailed multi-view datasets demonstrate that our model is capable of achieving superior performance. The code is released at https://github.com/cncq-tang/TMLC.

Zheyuan Hu, Yifei Shi · cambridge

In the post-Dennard era, optimizing embedded systems requires navigating complex trade-offs between energy efficiency and latency. Traditional heuristic tuning is often inefficient in such high-dimensional, non-smooth landscapes. In this work, we propose a Bayesian Optimization framework using Gaussian Processes to automate the search for optimal scheduling configurations on heterogeneous multi-core architectures. We explicitly address the multi-objective nature of the problem by approximating the Pareto Frontier between energy and time. Furthermore, by incorporating Sensitivity Analysis (fANOVA) and comparing different covariance kernels (e.g., Matérn vs. RBF), we provide physical interpretability to the black-box model, revealing the dominant hardware parameters driving system performance.

Yi Sun, Xin Xu, Jian Li et al.

It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability and restrict the learning plasticity of later tasks to avoid catastrophic forgetting of learned knowledge. Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion. In this strategy, a slow model with better stability, and a fast model with better plasticity are learned sequentially at the splitting stage. Then stability and plasticity are both kept by fusing the two models in an adaptive manner. Towards this end, we design an optimizer named Task-Preferred Null Space Projector(TPNSP) to the slow learning process for narrowing the fusion gap. To achieve better model fusion, we further design a Dreaming-Meta-Weighted fusion policy for better maintaining the old and new knowledge simultaneously, which doesn't require to use the previous datasets. Experimental results and analysis reported in this work demonstrate the superiority of the proposed method for maintaining networks stability and keeping its plasticity. Our code will be released.

Yuqing Lan, Yao Duan, Yifei Shi et al.

Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for context modeling. We argue that scene understanding benefits from object relation reasoning, which is capable of mitigating the ambiguity of 3D object detections and thus helps locate and classify the 3D objects more accurately and robustly. To achieve this, we propose a novel 3D relation module (3DRM) which reasons about object relations at pair-wise levels. The 3DRM predicts the semantic and spatial relationships between objects and extracts the object-wise relation features. We demonstrate the effects of 3DRM by plugging it into proposal-based and voting-based 3D object detection pipelines, respectively. Extensive evaluations show the effectiveness and generalization of 3DRM on 3D object detection. Our source code is available at https://github.com/lanlan96/3DRM.

Weishang Wu, Yifei Shi, Zhiping Cai

Task-oriented dexterous grasping remains challenging in robotic manipulations of open-world objects under severe partial observation, where significant missing data invalidates generic shape completion. In this paper, to overcome this limitation, we study Task-Oriented Shape Completion, a new task that focuses on completing the potential contact regions rather than the entire shape. We argue that shape completion for grasping should be explicitly guided by the downstream manipulation task. To achieve this, we first generate multiple task-oriented shape completion candidates by leveraging the zero-shot capabilities of object functional understanding from several pre-trained foundation models. A 3D discriminative autoencoder is then proposed to evaluate the plausibility of each generated candidate and optimize the most plausible one from a global perspective. A conditional flow-matching model named FlowGrasp is developed to generate task-oriented dexterous grasps from the optimized shape. Our method achieves state-of-the-art performance in task-oriented dexterous grasping and task-oriented shape completion, improving the Grasp Displacement and the Chamfer Distance over the state-of-the-art by 16.17\% and 55.26%, respectively. In particular, it shows good capabilities in grasping objects with severe missing data. It also demonstrates good generality in handling open-set categories and tasks.

Yifei Shi, Boyan Wan, Xin Xu et al.

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape reconstruction, novel view image synthesis, and more recently, object pose estimation. Neural implicit fields enable learning dense correspondences between the camera space and the object's canonical space-including unobserved regions in camera space-significantly boosting object pose estimation performance in challenging scenarios like highly occluded objects and novel shapes. Despite progress, predicting canonical coordinates for unobserved camera-space regions remains challenging due to the lack of direct observational signals. This necessitates heavy reliance on the model's generalization ability, resulting in high uncertainty. Consequently, densely sampling points across the entire camera space may yield inaccurate estimations that hinder the learning process and compromise performance. To alleviate this problem, we propose a method combining an SO(3)-equivariant convolutional implicit network and a positive-incentive point sampling (PIPS) strategy. The SO(3)-equivariant convolutional implicit network estimates point-level attributes with SO(3)-equivariance at arbitrary query locations, demonstrating superior performance compared to most existing baselines. The PIPS strategy dynamically determines sampling locations based on the input, thereby boosting the network's accuracy and training efficiency. Our method outperforms the state-of-the-art on three pose estimation datasets. Notably, it demonstrates significant improvements in challenging scenarios, such as objects captured with unseen pose, high occlusion, novel geometry, and severe noise.

Hao Qu, Lilian Zhang, Jun Mao et al.

The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information and perform well on matching benchmarks, they struggle with generalization in continuous motion scenes, adversely affecting loop detection accuracy. Our system employs a Model-Agnostic Meta-Learning (MAML) strategy to optimize the training of keypoint extraction networks, enhancing their adaptability to diverse environments. Additionally, we introduce a coarse-to-fine feature tracking mechanism for learned keypoints. It begins with a direct method to approximate the relative pose between consecutive frames, followed by a feature matching method for refined pose estimation. To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. Experimental evaluations on publicly available datasets demonstrate that DK-SLAM outperforms leading traditional and learning based SLAM systems, such as ORB-SLAM3 and LIFT-SLAM. These results underscore the efficacy and robustness of our DK-SLAM in varied and challenging real-world environments.

Le Shi, Yifei Shi, Xin Xu et al.

Recent advances in deep generative models demonstrate unprecedented zero-shot generalization capabilities, offering great potential for robot manipulation in unstructured environments. Given a partial observation of a scene, deep generative models could generate the unseen regions and therefore provide more context, which enhances the capability of robots to generalize across unseen environments. However, due to the visual artifacts in generated images and inefficient integration of multi-modal features in policy learning, this direction remains an open challenge. We introduce NVSPolicy, a generalizable language-conditioned policy learning method that couples an adaptive novel-view synthesis module with a hierarchical policy network. Given an input image, NVSPolicy dynamically selects an informative viewpoint and synthesizes an adaptive novel-view image to enrich the visual context. To mitigate the impact of the imperfect synthesized images, we adopt a cycle-consistent VAE mechanism that disentangles the visual features into the semantic feature and the remaining feature. The two features are then fed into the hierarchical policy network respectively: the semantic feature informs the high-level meta-skill selection, and the remaining feature guides low-level action estimation. Moreover, we propose several practical mechanisms to make the proposed method efficient. Extensive experiments on CALVIN demonstrate the state-of-the-art performance of our method. Specifically, it achieves an average success rate of 90.4\% across all tasks, greatly outperforming the recent methods. Ablation studies confirm the significance of our adaptive novel-view synthesis paradigm. In addition, we evaluate NVSPolicy on a real-world robotic platform to demonstrate its practical applicability.

Qifan Chen, Jin Cui, Cindy Duan et al.

Accurate estimation of postmenstrual age (PMA) at scan is crucial for assessing neonatal development and health. While deep learning models have achieved high accuracy in predicting PMA from brain MRI, they often function as black boxes, offering limited transparency and interpretability in clinical decision support. In this work, we address the dual challenge of accuracy and interpretability by adapting a multimodal large language model (MLLM) to perform both precise PMA prediction and clinically relevant explanation generation. We introduce a parameter-efficient fine-tuning (PEFT) strategy using instruction tuning and Low-Rank Adaptation (LoRA) applied to the Qwen2.5-VL-7B model. The model is trained on four 2D cortical surface projection maps derived from neonatal MRI scans. By employing distinct prompts for training and inference, our approach enables the MLLM to handle a regression task during training and generate clinically relevant explanations during inference. The fine-tuned model achieves a low prediction error with a 95 percent confidence interval of 0.78 to 1.52 weeks, while producing interpretable outputs grounded in developmental features, marking a significant step toward transparent and trustworthy AI systems in perinatal neuroscience.

Yi Sun, Xin Xu, Jian Li et al.

Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task inference routes. Due to the inconsistent optimization objectives, the task gradients used for training MONs will interfere with each other on the shared routes, which will decrease the overall model performance. To address this issue, we propose a novel gradient de-conflict algorithm named DR-MGF(Dynamic Routes and Meta-weighted Gradient Fusion) in this work. Different from existing de-conflict methods, DR-MGF achieves gradient de-conflict in MONs by learning task-preferred inference routes. The proposed method is motivated by our experimental findings: the shared filters are not equally important to different tasks. By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks. Through making the dominances of tasks over filters be proportional to the task-specific importance of filters, DR-MGF can effectively reduce the inter-task interference. The task-specific importance variables ultimately determine task-preferred inference routes at the end of training iterations. Extensive experimental results on CIFAR, ImageNet, and NYUv2 illustrate that DR-MGF outperforms the existing de-conflict methods both in prediction accuracy and convergence speed of MONs. Furthermore, DR-MGF can be extended to general MONs without modifying the overall network structures.

Wenbo Zhang, Jing Zhang, Yifei Shi et al.

With the large-scale deployment of industrial internet of things (IIoT) devices, the number of vulnerabilities that threaten IIoT security is also growing dramatically, including a mass of undisclosed IIoT vulnerabilities that lack mitigation measures. Coordination Vulnerabilities Disclosure (CVD) is one of the most popular vulnerabilities sharing solutions, in which some security workers (SWs) can develop undisclosed vulnerabilities patches together. However, CVD assumes that sharing participants (SWs) are all honest, and thus offering chances for dishonest SWs to leak undisclosed IIoT vulnerabilities. To combat such threats, we propose an Undisclosed IIoT Vulnerabilities Trusted Sharing Protection (UIV-TSP) scheme with dynamic token. In this article, a dynamic token is an implicit access credential for an SW to acquire an undisclosed vulnerability information, which is only held by the system and constantly updated as the SW access. Meanwhile, the latest updated token can be stealthily sneaked into the acquired information as the traceability token. Once the undisclosed vulnerability information leaves the SW host, the embedded self-destruct program will be automatically triggered to prevent leaks since the destination MAC address in the traceability token has changed. To quickly distinguish dishonest SWs, trust mechanism is adopted to evaluate the trust value of SWs. Moreover, we design a blockchain-assisted continuous logs storage method to achieve the tamper-proofing of dynamic token and the transparency of undisclosed IIoT vulnerabilities sharing. The simulation results indicate that our proposed scheme is resilient to suppress dishonest SWs and protect the IoT undisclosed vulnerabilities effectively.

Yifei Shi, Junwen Huang, Xin Xu et al.

We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from observed 3D point clouds. According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose. We train a deep neural network to regress 6D object pose based on geometrically stable patch groups via learning both intra-patch geometric features and inter-patch contextual features. A subnetwork is jointly trained to predict per-patch poses. This auxiliary task is a relaxation of the group pose prediction: A single patch cannot determine the full 6DoFs but is able to improve pose accuracy in its corresponding DoFs. Working with patch groups makes our method generalize well for random occlusion and unseen instances. The method is easily amenable to resolve symmetry ambiguities. Our method achieves the state-of-the-art results on public benchmarks compared not only to depth-only but also to RGBD methods. It also performs well in category-level pose estimation.

Yifei Shi, Junwen Huang, Hongjia Zhang et al.

We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.

Maciej Halber, Yifei Shi, Kai Xu et al.

In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these "rescans" to infer a temporal model of a scene with semantic instance information. Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to update the temporal model. The model contains object instance associations across time and thus can be used to track individual objects, even though there are only sparse observations. During experiments with a new benchmark for the new task, our algorithm outperforms alternate approaches based on state-of-the-art networks for semantic instance segmentation.

Yifei Shi, Angel Xuan Chang, Zhelun Wu et al.

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a variational denoising recursive autoencoder (VDRAE) that generates and iteratively refines a hierarchical representation of 3D object layouts, interleaving bottom-up encoding for context aggregation and top-down decoding for propagation. We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud. We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.

Yifei Shi, Kai Xu, Matthias Niessner et al.

We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in RGB, depth, and normal information of a planar patch in an image and outputs a descriptor that can be used to find coplanar patches from other images.We train the network on 10 million triplets of coplanar and non-coplanar patches, and evaluate on a new coplanarity benchmark created from commodity RGB-D scans. Experiments show that our learned descriptor outperforms alternatives extended for this new task by a significant margin. In addition, we demonstrate the benefits of coplanarity matching in a robust RGBD reconstruction formulation.We find that coplanarity constraints detected with our method are sufficient to get reconstruction results comparable to state-of-the-art frameworks on most scenes, but outperform other methods on standard benchmarks when combined with a simple keypoint method.

Min Liu, Yifei Shi, Lintao Zheng et al.

Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of attention-based models in 2D vision tasks based on single RGB images, we propose to address the multi-view depth-based active object recognition using attention mechanism, through developing an end-to-end recurrent 3D attentional network. The architecture takes advantage of a recurrent neural network (RNN) to store and update an internal representation. Our model, trained with 3D shape datasets, is able to iteratively attend to the best views targeting an object of interest for recognizing it. To realize 3D view selection, we derive a 3D spatial transformer network which is differentiable for training with backpropagation, achieving much faster convergence than the reinforcement learning employed by most existing attention-based models. Experiments show that our method, with only depth input, achieves state-of-the-art next-best-view performance in time efficiency and recognition accuracy.