Robust robotic grasping in cluttered environments presents a significant challenge, as existing methods often neglect the complex interactions between the gripper, objects, and obstacles, leading to collisions and grasping failures. To address this, we propose a framework that integrates collision avoidance as a core constraint within the grasp pose optimization process. Central to this framework is a Neural Collision Detection (NCD) network that takes scene configurations and grasp poses as inputs, producing a collision score that approximates traditional collision detection functions. The NCD network provides critical feedback for refining grasp predictions and demonstrates strong generalization across diverse environments, facilitating efficient collision detection and constrained grasp pose optimization. Additionally, we incorporate frictional force closure, geometric symmetry, and surface alignment as regularization terms within the optimization function, enhancing the physical stability and geometric plausibility of the generated grasps. Extensive experiments conducted in real-world environments show a significant improvement in grasp success rates, with robust generalization to previously unseen objects and scenarios. These results validate the efficacy of our framework, highlighting its potential for enabling reliable robotic manipulation in complex and cluttered environments.

Neural fields, also known as coordinate-based multi-layer perceptrons (MLPs), have recently achieved impressive results in representing low-dimensional data. Unlike convolutional neural networks (CNNs), MLPs are globally connected and lack local control; adjusting a local region leads to global changes. Therefore, improving local neural fields usually leads to a dilemma: filtering out local artifacts can simultaneously smooth away desired details. Our solution is a new filtering technique that consists of two counteractive operators: a smoothing operator that provides global smoothing for better generalization and a recovery operator that provides better controllability for local adjustments. We found that using either operator alone could lead to an increase in noisy artifacts or oversmoothed regions. By combining the two operators, smoothing and sharpening can be adjusted to first smooth the entire region and then recover fine-grained details in the overly smoothed regions. Thus, our filter helps neural fields remove significant noise while enhancing the details. We demonstrate the benefits of our filter on various tasks, where it shows significant improvements over state-of-the-art methods. Moreover, our filter provides a better performance in terms of convergence speed and network stability.

As a widely used method in signal processing, Principal Component Analysis (PCA) performs both the compression and the recovery of high dimensional data by leveraging the linear transformations. Considering the robustness of PCA, how to discriminate correct samples and outliers in PCA is a crucial and challenging issue. In this paper, we present a general model, which conducts PCA via a non-decreasing concave regularized minimization and is termed PCA-NCRM for short. Different from most existing PCA methods, which learn the linear transformations by minimizing the recovery errors between the recovered data and the original data in the least squared sense, our model adopts the monotonically non-decreasing concave function to enhance the ability of model in distinguishing correct samples and outliers. To be specific, PCA-NCRM enlarges the attention to samples with smaller recovery errors and diminishes the attention to samples with larger recovery errors at the same time. The proposed minimization problem can be efficiently addressed by employing an iterative re-weighting optimization. Experimental results on several datasets show the effectiveness of our model.

Recently, coordinate-based MLPs have been shown to be powerful representations for 3D surfaces, where learning high-frequency details is facilitated by modulating surface functions with periodic functions [1], [2]. While shortening the periodicity helps in learning high frequencies, it leads to increasing ambiguity, i.e., more points along the axis directions become similar in the embedded space, so that many points on the surface and outside the surface have similar predictions. In addition, short periodicity increases local geometric variations, leading to unexpected noisy artifacts in untrained regions. Unlike existing methods that learn surface functions in a regular cube, we find surfaces within shells, a coarse form of the target surfaces constructed by a binary classifier. The advantage of build surfaces in shells is that MLPs focus on regions of interest, which inherently reduces ambiguity and also promotes training efficiency and test accuracy. We demonstrate the effectiveness of shells and show significant improvements over baseline methods in 3D surface reconstruction from raw point clouds.

Visual (re)localization addresses the problem of estimating the 6-DoF (Degree of Freedom) camera pose of a query image captured in a known scene, which is a key building block of many computer vision and robotics applications. Recent advances in structure-based localization solve this problem by memorizing the mapping from image pixels to scene coordinates with neural networks to build 2D-3D correspondences for camera pose optimization. However, such memorization requires training by amounts of posed images in each scene, which is heavy and inefficient. On the contrary, few-shot images are usually sufficient to cover the main regions of a scene for a human operator to perform visual localization. In this paper, we propose a scene region classification approach to achieve fast and effective scene memorization with few-shot images. Our insight is leveraging a) pre-learned feature extractor, b) scene region classifier, and c) meta-learning strategy to accelerate training while mitigating overfitting. We evaluate our method on both indoor and outdoor benchmarks. The experiments validate the effectiveness of our method in the few-shot setting, and the training time is significantly reduced to only a few minutes.11Code available at: https://github.com/siyandong/SRC

We present a multiscale deformed implicit surface network (MDISN) to reconstruct 3D objects from single images by adapting the implicit surface of the target object from coarse to fine to the input image. The basic idea is to optimize the implicit surface according to the change of consecutive feature maps from the input image. And with multi-resolution feature maps, the implicit field is refined progressively, such that lower resolutions outline the main object components, and higher resolutions reveal fine-grained geometric details. To better explore the changes in feature maps, we devise a simple field deformation module that receives two consecutive feature maps to refine the implicit field with finer geometric details. Experimental results on both synthetic and real-world datasets demonstrate the superiority of the proposed method compared to state-of-the-art methods.

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.

Surface remeshing is widely required in modeling, animation, simulation, and many other computer graphics applications. Improving the elements’ quality is a challenging task in surface remeshing. Existing methods often fail to efficiently remove poor-quality elements especially in regions with sharp features. In this paper, we propose and use a robust segmentation method followed by remeshing the segmented mesh. Mesh segmentation is initiated using an existing Live-wire interaction approach and is further refined using local mesh operations. The refined segmented mesh is finally sent to the remeshing pipeline, in which each mesh segment is remeshed independently. An experimental study compares our mesh segmentation method as well as remeshing results with representative existing methods. We demonstrate that the proposed segmentation method is robust and suitable for remeshing.

We present an algorithm for segmenting a mesh into patches whose boundaries are aligned with prominent ridge and valley lines of the shape. Our key insight is that this problem can be formulated as correlation clustering (CC), a graph partitioning problem originating from the data mining community. The formulation lends two unique advantages to our method over existing segmentation methods. First, since CC is non-parametric, our method has few parameters to tune. Second, as CC is governed by edge weights in the graph, our method offers users direct and local control over the segmentation result. Our technical contributions include the construction of the weighted graph on which CC is defined, a strategy for rapidly computing CC on this graph, and an interactive tool for editing the segmentation. Our experiments show that our method produces qualitatively better segmentations than existing methods on a wide range of inputs.

We present a deformation-driven approach to topology-varying 3D shape correspondence. In this paradigm, the best correspondence between two shapes is the one that results in a minimal-energy, possibly topology-varying, deformation that transforms one shape to conform to the other while respecting the correspondence. Our deformation model, called GeoTopo transform , allows both geometric and topological operations such as part split, duplication, and merging, leading to fine-grained and piecewise continuous correspondence results. The key ingredient of our correspondence scheme is a deformation energy that penalizes geometric distortion, encourages structure preservation, and simultaneously allows topology changes. This is accomplished by connecting shape parts using structural rods , which behave similarly to virtual springs but simultaneously allow the encoding of energies arising from geometric, structural, and topological shape variations. Driven by the combined deformation energy, an optimal shape correspondence is obtained via a pruned beam search. We demonstrate our deformation-driven correspondence scheme on extensive sets of man-made models with rich geometric and topological variation and compare the results to state-of-the-art approaches.

Abstract We present an interactive method for mesh segmentation that is inspired by the classical live‐wire interaction for image segmentation. The core contribution of the work is the definition and computation of wires on surfaces that are likely to lie at segment boundaries. We define wires as geodesics in a new tensor‐based anisotropic metric, which improves upon previous metrics in stability and feature‐awareness. We further introduce a simple but effective mesh embedding approach that allows geodesic paths in an anisotropic path to be computed efficiently using existing algorithms designed for Euclidean geodesics. Our tool is particularly suited for delineating segmentation boundaries that are aligned with features or curvature directions, and we demonstrate its use in creating artist‐guided segmentations.

Generating surfaces from 3D curve networks has been a longstanding problem in computer graphics. Recent attention to this area has resurfaced as a result of new sketch based modeling systems. In this work we present a new algorithm for finding cycles that bound surface patches. Unlike prior art in this area, the output of our technique is unrestricted, generating both manifold and non-manifold geometry with arbitrary genus. The novel insight behind our method is to formulate our problem as finding local mappings at the vertices and curves of our network, where each mapping describes how incident curves are grouped into cycles. This approach lends us the efficiency necessary to present our system in an interactive design modeler, whereby the user can adjust patch constraints and change the manifold properties of curves while the system automatically re-optimizes the solution.