This paper introduces CN-RMA, a novel approach for 3D indoor object detection from multi-view images. We observe the key challenge as the ambiguity of image and 3D correspondence without explicit geometry to provide occlusion information. To address this issue, CN-RMA leverages the synergy of 3D reconstruction networks and 3D object detection networks, where the reconstruction network provides a rough Truncated Signed Distance Function (TSDF) and guides image features to vote to 3D space correctly in an end-to-end manner. Specifically, we associate weights to sampled points of each ray through ray marching, representing the contribution of a pixel in an image to corresponding 3D locations. Such weights are determined by the predicted signed distances so that image features vote only to regions near the reconstructed surface. Our method achieves state-of-the-art performance in 3D object detection from multi-view images, as measured by [email protected] and [email protected] on the ScanNet and ARKitScenes datasets. The code and models are released at https://github.com/SerCharles/CN-RMA.

Advancements in 3D instance segmentation have tra-ditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories. Recent efforts have sought to har-ness vision-language models like CLIP for open-set semantic reasoning, yet these methods struggle to distinguish between objects of the same categories and rely on specific prompts that are not universally applicable. In this paper, we introduce SAI3D, a novel zero-shot 3D instance segmentation approach that synergistically leverages geometric priors and semantic cues derived from Segment Any-thing Model (SAM). Our method partitions a 3D scene into geometric primitives, which are then progressively merged into 3D instance segmentations that are consistent with the multi-view SAM masks. Moreover, we design a hierarchi-cal region-growing algorithm with a dynamic thresholding mechanism, which largely improves the robustness of fine-grained 3D scene parsing. Empirical evaluations on Scan-Net, Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach. No-tably, SAI3D outperforms existing open-vocabulary base-lines and even surpasses fully-supervised methods in class-agnostic segmentation on ScanNet++. Our project page is at https://yd-yin.github.io/SAI3D.

We propose a unified 3D flow framework for joint learning of shape embedding and deformation for different categories. Our goal is to recover shapes from imperfect point clouds by fitting the best shape template in a shape repository after deformation. Accordingly, we learn a shape embedding for template retrieval and a flow-based network for robust deformation. We note that the deformation flow can be quite different for different shape categories. Therefore, we introduce a novel multi-hub module to learn multiple modes of deformation to incorporate such variation, providing a network which can handle a wide range of objects from different categories. The shape embedding is designed to retrieve the best-fit template as the nearest neighbor in a latent space. We replace the standard fully connected layer with a tiny structure in the embedding that significantly reduces network complexity and further improves deformation quality. Experiments show the superiority of our method to existing state-of-the-art methods via qualitative and quantitative comparisons. Finally, our method provides efficient and flexible deformation that can further be used for novel shape design.

We focus on learning descriptive geometry and motion features from 4D point cloud sequences in this work. Existing works usually develop generic 4D learning tools without leveraging the prior that a 4D sequence comes from a single 3D scene with local dynamics. Based on this observation, we propose to learn region-wise coordinate frames that transform together with the underlying geometry. With such frames, we can factorize geometry and motion to facilitate a feature-space geometric reconstruction for more effective 4D learning. To learn such region frames, we develop a rotation equivariant network with a frame stabilization strategy. To leverage such frames for better spatial-temporal feature learning, we develop a frame-guided 4D learning scheme. Experiments show that this approach significantly outperforms previous state-of-the-art methods on a wide range of 4D understanding benchmarks.

Large-scale vector mapping is the foundation for transportation and urban planning. Most existing mapping methods are tailored to one specific mapping task, due to task-specific requirements on shape regularization and topology reconstruction. We propose GraphMapper, a unified framework for end-to-end vector map extraction from satellite images. Our key idea is using primitive graph as a unified representation of vector maps and formulating shape regularization and topology reconstruction as primitive graph reconstruction problems that can be solved in the same framework. Specifically, shape regularization is modeled as the consistency between primitive directions and their pairwise relationship. Based on the primitive graph, we design a learning approach to reconstruct primitive graphs in multiple stages. GraphMapper can fully explore primitive-wise and pairwise information for shape regularization and topology reconstruction, resulting improved primitive graph learning capabilities. We empirically demonstrate the effectiveness of GraphMapper on two challenging mapping tasks for building footprints and road networks. With the premise of sharing the majority design of the architecture and a few task-specific designs, our model outperforms state-of-the-art methods in both tasks on public benchmarks. Our code will be publicly available.

We present LocalPose, a novel method for 9 DoF object pose estimation from object point clouds. Existing works regress pose directly from the global shape embedding and are limited to a fixed set of shapes. We identify that the global object pose is closely related to local geometry properties like surface orientations at representative regions. Therefore, our key idea is to summarize local geometry properties as pose signatures at each point and aggregate them into the global pose, where local pose signatures are easier to learn by the network and generalize to novel shapes. We find two types of pose signatures that benefit pose estimation. First, we learn a neural network to predict 9 DoF pose signatures as pose candidates, and the process of voting them for the object pose. Second, we treat surface normals as direct pose regulators who help to select a subset of pose candidates to achieve the best accuracy. Experiments show that our method outperforms the state-of-the-art in terms of fine-grained pose accuracy on synthetic and real datasets, contributed by both pose signatures as candidates and regulators.

We present a novel vectorized indoor modeling approach that converts point clouds into building information models (BIM) with concise and semantically segmented polygonal meshes. Existing methods detect planar shapes and connect them to complete the scene. Some focus on floor plan reconstruction as a simplified problem to better analyze connectivity between planes of floors and walls. However, the connectivity analysis is still challenging and ill-posed with incomplete point clouds as input. We propose ArrangementNet to estimate scene arrangements from an incomplete point cloud, which we can easily convert into a BIM model. ArrangementNet is a novel graph neural network that consumes noisy over-partitioned initial arrangements extracted through non-learning techniques and outputs high-quality scene arrangement. The core of ArrangementNet is an extended graph convolution that leverages co-linear and co-face relationships in the arrangement and improves the quality of prediction in complex scenes. We apply ArrangementNet to improve floor plan and ceiling arrangements and enrich them with semantic objects as scene arrangements for scene generation. Our approach faithfully models challenging scenes obtained from laser scans or multiview stereo and shows significant improvement in BIM model reconstruction compared to the state-of-the-art. Our code is available at https://github.com/zssjh/ArrangementNet.

We present MVLayoutNet, a network for holistic 3D reconstruction from multi-view panoramas. Our core contribution is to seamlessly combine learned monocular layout estimation and multi-view stereo (MVS) for accurate layout reconstruction in both 3D and image space. We jointly train a layout module to produce an initial layout and a novel MVS module to obtain accurate layout geometry. Unlike standard MVSNet, our MVS module takes a newly-proposed layout cost volume, which aggregates multi-view costs at the same depth layer into corresponding layout elements. We additionally provide an attention-based scheme that guides the MVS module to focus on structural regions. Such a design considers both local pixel-level costs and global holistic information for better reconstruction. Experiments show that our method outperforms state-of-the-arts in terms of depth rmse by 21.7% and 41.2% on the 2D-3D-S [1] and ZInD [4] datasets. For complex scenes with multiple rooms, our method can be applied to each layout element of a precomputed topology to accurately reconstruct a globally coherent layout geometry.

We propose a novel approach for large-scale nonlinear least squares problems based on deep learning frameworks. Nonlinear least squares are commonly solved with the Levenberg-Marquardt (LM) algorithm for fast convergence. We implement a general and efficient LM solver on a deep learning framework by designing a new backward jacobian network to enable automatic sparse jacobian matrix computation. Furthermore, we introduce a stochastic domain decomposition approach that enables batched optimization and preserves convergence for large problems. We evaluate our method by solving bundle adjustment as a fundamental problem. Experiments show that our optimizer significantly outperforms the state-of-the-art solutions and existing deep learning solvers considering quality, efficiency, and memory. Our stochastic domain decomposition enables distributed optimization, consumes little memory and time, and achieves similar quality compared to a global solver. As a result, our solver effectively solves nonlinear least squares on an extremely large scale. Our code will be available based on Pytorch1and Mindspore2.

We present PrimitiveNet, a novel approach for high-resolution primitive instance segmentation from point clouds on a large scale. Our key idea is to transform the global segmentation problem into easier local tasks. We train a high-resolution primitive embedding network to predict explicit geometry features and implicit latent features for each point. The embedding is jointly trained with an adversarial network as a primitive discriminator to decide whether points are from the same primitive instance in local neighborhoods. Such local supervision encourages the learned embedding and discriminator to describe local surface properties and robustly distinguish different instances. At inference time, network predictions are followed by a region growing method to finalize the segmentation. Experiments show that our method outperforms existing state-of-the-arts based on mean average precision by a significant margin (46.3%) on ABC dataset [31]. We can process extremely large real scenes covering more than 0.1km2. Ablation studies highlight the contribution of our core designs. Finally, our method can improve geometry processing algorithms to abstract scans as lightweight models. Code and data will be available based on Pytorch1and Mindspore2.

In this paper, we proposed EPP-MVSNet, a novel deep learning network for 3D reconstruction from multi-view stereo (MVS). EPP-MVSNet can accurately aggregate features at high resolution to a limited cost volume with an optimal depth range, thus, leads to effective and efficient 3D construction. Distinct from existing works which measure feature cost at discrete positions which affects the 3D reconstruction accuracy, EPP-MVSNet introduces an epipolar-assembling-based kernel that operates on adaptive intervals along epipolar lines for making full use of the image resolution. Further, we introduce an entropy-based refining strategy where the cost volume describes the space geometry with the little redundancy. Moreover, we design a light-weighted network with Pseudo-3D convolutions integrated to achieve high accuracy and efficiency. We have conducted extensive experiments on challenging datasets Tanks & Temples(TNT), ETH3D and DTU. As a result, we achieve promising results on all datasets and the highest F-Score on the online TNT intermediate benchmark. Code is available at https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/eppmvsnet.

Realistic color texture generation is an important step in RGB-D surface reconstruction, but remains challenging in practice due to inaccuracies in reconstructed geometry, misaligned camera poses, and view-dependent imaging artifacts. In this work, we present a novel approach for color texture generation using a conditional adversarial loss obtained from weakly-supervised views. Specifically, we propose an approach to produce photorealistic textures for approximate surfaces, even from misaligned images, by learning an objective function that is robust to these errors. The key idea of our approach is to learn a patch-based conditional discriminator which guides the texture optimization to be tolerant to misalignments. Our discriminator takes a synthesized view and a real image, and evaluates whether the synthesized one is realistic, under a broadened definition of realism. We train the discriminator by providing as `real' examples pairs of input views and their misaligned versions - so that the learned adversarial loss will tolerate errors from the scans. Experiments on synthetic and real data under quantitative or qualitative evaluation demonstrate the advantage of our approach in comparison to state of the art (see Figure 1, right). Our code is publicly available1with video demonstration2.

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or diversity. In this paper, we introduce Local Implicit Grid Representations, a new 3D shape representation designed for scalability and generality. The motivating idea is that most 3D surfaces share geometric details at some scale - i.e., at a scale smaller than an entire object and larger than a small patch. We train an autoencoder to learn an embedding of local crops of 3D shapes at that size. Then, we use the decoder as a component in a shape optimization that solves for a set of latent codes on a regular grid of overlapping crops such that an interpolation of the decoded local shapes matches a partial or noisy observation. We demonstrate the value of this proposed approach for 3D surface reconstruction from sparse point observations, showing significantly better results than alternative approaches.

We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology, yet preserves fine geometric details. Different from a generative space where a latent vector is directly decoded into a shape, a deformation space decodes a vector into a continuous flow that can advect a source shape towards a target. Such a space naturally allows the disentanglement of geometric style (coming from the source) and structural pose (conforming to the target). We parametrize the deformation between geometries as a learned continuous flow field via a neural network and show that such deformations can be guaranteed to have desirable properties, such as bijectivity, freedom from self-intersections, or volume preservation. We illustrate the effectiveness of this learned deformation space for various downstream applications, including shape generation via deformation, geometric style transfer, unsupervised learning of a consistent parameterization for entire classes of shapes, and shape interpolation.

We introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps). The key idea is to utilize a 4-rotational symmetric(4-RoSy) field to define a domain for convolution on a surface. Though 4-RoSy fields have several properties favor-able for convolution on surfaces (low distortion, few singularities, consistent parameterization, etc.), orientations are ambiguous up to 4-fold rotation at any sample point. So, we introduce a new convolutional operator invariant to the4-RoSy ambiguity and use it in a network to extract features from high-resolution signals on geodesic neighborhoods of a surface. In comparison to alternatives, such as PointNet-based methods which lack a notion of orientation, the coherent structure given by these neighborhoods results in significantly stronger features. As an example application, we demonstrate the benefits of our architecture for 3D semantic segmentation of textured 3D meshes. The results show that our method outperforms all existing methods on the basis of mean IoU by a significant margin in both geometry-only(6.4%) and RGB+Geometry (6.9-8.2%) settings.

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level'' 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)-a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

In this work, we introduce the novel problem of identifying dense canonical 3D coordinate frames from a single RGB image. We observe that each pixel in an image corresponds to a surface in the underlying 3D geometry, where a canonical frame can be identified as represented by three orthogonal axes, one along its normal direction and two in its tangent plane. We propose an algorithm to predict these axes from RGB. Our first insight is that canonical frames computed automatically with recently introduced direction field synthesis methods can provide training data for the task. Our second insight is that networks designed for surface normal prediction provide better results when trained jointly to predict canonical frames, and even better when trained to also predict 2D projections of canonical frames. We conjecture this is because projections of canonical tangent directions often align with local gradients in images, and because those directions are tightly linked to 3Dcanonical frames through projective geometry and orthogonality constraints. In our experiments, we find that our method predicts 3D canonical frames that can be used in applications ranging from surface normal estimation, feature matching, and augmented reality.

We present a simple yet effective end-to-end trainable deep network with geometry-inspired convolutional operators for detecting vanishing points in images. Traditional convolutional neural networks rely on aggregating edge features and do not have mechanisms to directly exploit the geometric properties of vanishing points as the intersections of parallel lines. In this work, we identify a canonical conic space in which the neural network can effectively compute the global geometric information of vanishing points locally, and we propose a novel operator named conic convolution that can be implemented as regular convolutions in this space. This new operator explicitly enforces feature extractions and aggregations along the structural lines and yet has the same number of parameters as the regular 2D convolution. Our extensive experiments on both synthetic and real-world datasets show that the proposed operator significantly improves the performance of vanishing point detection over traditional methods. The code and dataset have been made publicly available at https://github.com/zhou13/neurvps.

Abstract QuadriFlow is a scalable algorithm for generating quadrilateral surface meshes based on the Instant Field‐Aligned Meshes of Jakob et al. (ACM Trans. Graph. 34(6):189, 2015). We modify the original algorithm such that it efficiently produces meshes with many fewer singularities. Singularities in quadrilateral meshes cause problems for many applications, including parametrization and rendering with Catmull‐Clark subdivision surfaces. Singularities can rarely be entirely eliminated, but it is possible to keep their number small. Local optimization algorithms usually produce meshes with many singularities, whereas the best algorithms tend to require non‐local optimization, and therefore are slow. We propose an efficient method to minimize singularities by combining the Instant Meshes objective with a system of linear and quadratic constraints. These constraints are enforced by solving a global minimum‐cost network flow problem and local boolean satisfiability problems. We have verified the robustness and efficiency of our method on a subset of ShapeNet comprising 17,791 3D objects in the wild. Our evaluation shows that the quality of the quadrangulations generated by our method is as good as, if not better than, those from other methods, achieving about four times fewer singularities than Instant Meshes. Other algorithms that produce similarly few singularities are much slower; we take less than ten seconds to process each model. Our source code is publicly available.

We present a novel method for posing and animating botanical tree models interactively in real time. Unlike other state of the art methods which tend to produce trees that are overly flexible, bending and deforming as if they were underwater plants, our approach allows for arbitrarily high stiffness while still maintaining real-time frame rates without spurious artifacts, even on quite large trees with over ten thousand branches. This is accomplished by using an articulated rigid body model with as-stiff-as-desired rotational springs in conjunction with our newly proposed simulation technique, which is motivated both by position based dynamics and the typical algorithms for articulated rigid bodies. The efficiency of our algorithm allows us to pose and animate trees with millions of branches or alternatively simulate a small forest comprised of many highly detailed trees. Even using only a single CPU core, we can simulate ten thousand branches in real time while still maintaining quite crisp user interactivity. This has allowed us to incorporate our framework into a commodity game engine to run interactively even on a low-budget tablet. We show that our method is amenable to the incorporation of a large variety of desirable effects such as wind, leaves, fictitious forces, collisions, fracture, etc.

Recent breakthroughs in consumer level virtual reality (VR) headsets are creating a growing user-base in demand for immersive, full 3D VR experiences. While monoscopic 360-videos are perhaps the most prevalent type of content for VR headsets, they lack 3D information and thus cannot be viewed with full 6 degree-of-freedom (DOF). We present an approach that addresses this limitation via a novel warping algorithm that can synthesize new views both with rotational and translational motion of the viewpoint. This enables the ability to perform VR playback of input monoscopic 360-videos files in full stereo with full 6-DOF of head motion. Our method synthesizes novel views for each eye in accordance with the 6-DOF motion of the headset. Our solution tailors standard structure-from-motion and dense reconstruction algorithms to work accurately for 360-videos and is optimized for GPUs to achieve VR frame rates (>120 fps). We demonstrate the effectiveness our approach on a variety of videos with interesting content.

We present 3DLite 1 , a novel approach to reconstruct 3D environments using consumer RGB-D sensors, making a step towards directly utilizing captured 3D content in graphics applications, such as video games, VR, or AR. Rather than reconstructing an accurate one-to-one representation of the real world, our method computes a lightweight, low-polygonal geometric abstraction of the scanned geometry. We argue that for many graphics applications it is much more important to obtain high-quality surface textures rather than highly-detailed geometry. To this end, we compensate for motion blur, auto-exposure artifacts, and micro-misalignments in camera poses by warping and stitching image fragments from low-quality RGB input data to achieve high-resolution, sharp surface textures. In addition to the observed regions of a scene, we extrapolate the scene geometry, as well as the mapped surface textures, to obtain a complete 3D model of the environment. We show that a simple planar abstraction of the scene geometry is ideally suited for this completion task, enabling 3DLite to produce complete, lightweight, and visually compelling 3D scene models. We believe that these CAD-like reconstructions are an important step towards leveraging RGB-D scanning in actual content creation pipelines.

Large 3D model repositories of common objects are now ubiquitous and are increasingly being used in computer graphics and computer vision for both analysis and synthesis tasks. However, images of objects in the real world have a richness of appearance that these repositories do not capture, largely because most existing 3D models are untextured. In this work we develop an automated pipeline capable of transporting texture information from images of real objects to 3D models of similar objects. This is a challenging problem, as an object's texture as seen in a photograph is distorted by many factors, including pose, geometry, and illumination. These geometric and photometric distortions must be undone in order to transfer the pure underlying texture to a new object --- the 3D model. Instead of using problematic dense correspondences, we factorize the problem into the reconstruction of a set of base textures (materials) and an illumination model for the object in the image. By exploiting the geometry of the similar 3D model, we reconstruct certain reliable texture regions and correct for the illumination, from which a full texture map can be recovered and applied to the model. Our method allows for large-scale unsupervised production of richly textured 3D models directly from image data, providing high quality virtual objects for 3D scene design or photo editing applications, as well as a wealth of data for training machine learning algorithms for various inference tasks in graphics and vision.

We present an automatic thumbnail generation technique based on two essential considerations: how well they visually represent the original photograph, and how well the foreground can be recognized after the cropping and downsizing steps of thumbnailing. These factors, while important for the image indexing purpose of thumbnails, have largely been ignored in previous methods, which instead are designed to highlight salient content while disregarding the effects of downsizing. We propose a set of image features for modeling these two considerations of thumbnails, and learn how to balance their relative effects on thumbnail generation through training on image pairs composed of photographs and their corresponding thumbnails created by an expert photographer. Experiments show the effectiveness of this approach on a variety of images, as well as its advantages over related techniques.

Although finding correspondences between similar images is an important problem in image processing, the existing algorithms cannot find accurate and dense correspondences in images with significant changes in lighting/transformation or with the non-rigid objects. This paper proposes a novel method for finding accurate and dense correspondences between images even in these difficult situations. Starting with the non-rigid dense correspondence algorithm [1] to generate an initial correspondence map, we propose a new geometric filter that uses cubic B-Spline surfaces to approximate the correspondence mapping functions for shared objects in both images, thereby eliminating outliers and noise. We then propose an iterative algorithm which enlarges the region containing valid correspondences. Compared with the existing methods, our method is more robust to significant changes in lighting, color, or viewpoint. Furthermore, we demonstrate how to extend our surface approximation method to video editing by first generating a reliable correspondence map between a given source frame and each frame of a video. The user can then edit the source frame, and the changes are automatically propagated through the entire video using the correspondence map. To evaluate our approach, we examine applications of unsupervised image recognition and video texture editing, and show that our algorithm produces better results than those from state-of-the-art approaches.