We study the use of image-based Vision-Language Models (VLMs) for open-vocabulary segmentation of lidar scans in driving settings. Classically, image semantics can be back-projected onto 3D point clouds. Yet, resulting point labels are noisy and sparse. We consolidate these labels to enforce both spatio-temporal consistency and robustness to image-level augmentations. We then train a 3D network based on these refined labels. This simple method, called LOSC, outperforms the SOTA of zero-shot open-vocabulary semantic and panoptic segmentation on both nuScenes and SemanticKITTI, with significant margins. Code is available at https://github.com/valeoai/LOSC.

Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this problem with the task of class-agnostic unsupervised online instance segmentation and tracking. To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects. Our network is trained on pseudo-labels, eliminating the need for manual annotations. We conduct an evaluation using metrics adapted for temporal instance segmentation. Computing these metrics requires temporally-consistent instance labels. When unavailable, we construct these labels using the available 3D bounding boxes and semantic labels in the dataset. We compare our method against strong baselines and demonstrate its superiority across two different outdoor Lidar datasets. Project page: csautier.github.io/unit

Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM.

We present a comprehensive survey and benchmark of both traditional and learning-based methods for surface reconstruction from point clouds. This task is particularly challenging for real-world acquisitions due to factors such as noise, outliers, non-uniform sampling, and missing data. Traditional approaches often simplify the problem by imposing handcrafted priors on either the input point clouds or the resulting surface, a process that can require tedious hyperparameter tuning. In contrast, deep learning models have the capability to directly learn the properties of input point clouds and desired surfaces from data. We study the influence of handcrafted and learned priors on the precision and robustness of surface reconstruction techniques. We evaluate various time-tested and contemporary methods in a standardized manner. When both trained and evaluated on point clouds with identical characteristics, the learning-based models consistently produce higher-quality surfaces compared to their traditional counterparts-even in scenarios involving novel shape categories. However, traditional methods demonstrate greater resilience to the diverse anomalies commonly found in real-world 3D acquisitions. For the benefit of the research community, we make our code and datasets available, inviting further enhancements to learning-based surface reconstruction. This can be accessed at https://github.com/raphaelsulzer/dsr-benchmark.

Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large performance discrepancies due for instance to different lidar patterns or changes in acquisition conditions. This paper addresses the corresponding Unsupervised Domain Adaptation (UDA) task for semantic segmentation. To mitigate this problem, we introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. This novel strategy differs from classical minimization of statistical divergences or lidar-specific domain adaptation techniques. Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.The project repository: github.com/valeoai/SALUDA

We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar scans captured in the same scene. Several such approaches have been proposed in the literature from PointConstrast [40], which uses a contrast at the level of points, to the state-of-the-art TARL [30], which uses a contrast at the level of segments, roughly corresponding to objects. While the former enjoys a great simplicity of implementation, it is surpassed by the latter, which however requires a costly pre-processing. In BEVContrast, we define our contrast at the level of 2D cells in the Bird’s Eye View plane. Resulting cell-level representations offer a good trade-off between the point-level representations exploited in PointContrast and segment-level representations exploited in TARL: we retain the simplicity of PointContrast (cell representations are cheap to compute) while surpassing the performance of TARL in downstream semantic segmentation. The code is available at github.com/valeoai/BEVContrast

The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects. To address this limitation, we propose an approach that takes a single image of a new object as input and pre-dicts the relative pose of this object in new images without prior knowledge of the object's 3D model and without re-quiring training time for new objects and categories. We achieve this by training a model to directly predict discrim-inative embeddings for viewpoints surrounding the object. This prediction is done using a simple U-Net architecture with attention and conditioned on the desired pose, which yields extremely fast inference. We compare our approach to state-of-the-art methods and show it outperforms them both in terms of accuracy and robustness.

Self-supervised image backbones can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. Ideally, 3D backbones for lidar should be able to inherit these properties after distillation of these powerful 2D features. The most recent methods for image-to-lidar distillation on autonomous driving data show promising results, obtained thanks to distillation methods that keep improving. Yet, we still notice a large performance gap when measuring by linear probing the quality of distilled vs fully supervised features. In this work, instead of focusing only on the distillation method, we study the effect of three pillars for distillation: the 3D backbone, the pretrained 2D backbone, and the pretraining 2D+3D dataset. In particular, thanks to our scalable distillation method named ScaLR, we show that scaling the 2D and 3D backbones and pretraining on diverse datasets leads to a substantial improvement of the feature quality. This allows us to significantly reduce the gap between the quality of distilled and fully-supervised 3D features, and to improve the robustness of the pretrained backbones to domain gaps and perturbations. The code is available at https://github.com/valeoai/ScaLR.

We propose ManiPose, a manifold-constrained multi-hypothesis model for human-pose 2D-to-3D lifting. We provide theoretical and empirical evidence that, due to the depth ambiguity inherent to monocular 3D human pose estimation, traditional regression models suffer from pose-topology consistency issues, which standard evaluation metrics (MPJPE, P-MPJPE and PCK) fail to assess. ManiPose addresses depth ambiguity by proposing multiple candidate 3D poses for each 2D input, each with its estimated plausibility. Unlike previous multi-hypothesis approaches, ManiPose forgoes generative models, greatly facilitating its training and usage. By constraining the outputs to lie on the human pose manifold, ManiPose guarantees the consistency of all hypothetical poses, in contrast to previous works. We showcase the performance of ManiPose on real-world datasets, where it outperforms state-of-the-art models in pose consistency by a large margin while being very competitive on the MPJPE metric.

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with techniques which use other point cloud representations, achieve state-of-the-art results. Today, projection-based methods leverage 2D CNNs but recent advances in computer vision show that vision transformers (ViTs) have achieved state-of-the-art results in many image- based benchmarks. In this work, we question if projection- based methods for 3D semantic segmentation can benefit from these latest improvements on ViTs. We answer positively but only after combining them with three key ingredients: (a) ViTs are notoriously hard to train and require a lot of training data to learn powerful representations. By preserving the same backbone architecture as for RGB images, we can exploit the knowledge from long training on large image collections that are much cheaper to acquire and annotate than point clouds. We reach our best results with pre-trained ViTs on large image datasets. (b) We compensate ViTs' lack of inductive bias by substituting a tailored convolutional stem for the classical linear embedding layer. (c) We refine pixel-wise predictions with a convolutional decoder and a skip connection from the convolutional stem to combine low-level but fine-grained features of the the convolutional stem with the high-level but coarse predictions of the ViT encoder. With these ingredients, we show that our method, called RangeViT, outperforms existing projection-based methods on nuScenes and SemanticKITTI. The code is available at https://github.com/valeoai/rangevit.

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled, and to use the underlying latent vectors as input to the perception head. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information, that can be used to boost an actual perception task. This principle has a very simple formulation, which makes it both easy to implement and widely applicable to a large range of 3D sensors and deep networks performing semantic segmentation or object detection. In fact, it supports a single-stream pipeline, as opposed to most contrastive learning approaches, allowing training on limited resources. We conducted extensive experiments on various autonomous driving datasets, involving very different kinds of lidars, for both semantic segmentation and object detection. The results show the effectiveness of our method to learn useful representations without any annotation, compared to existing approaches. The code is available at github.com/valeoai/ALSO

Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently. Sparse 3D convolutions have become the de-facto tools to construct deep neural networks for this task: they exploit point cloud sparsity to reduce the memory and computational loads and are at the core of today's best methods. In this paper, we propose an alternative method that reaches the level of state-of-the-art methods without requiring sparse convolutions. We actually show that such level of performance is achievable by relying on tools a priori unfit for large scale and high-performing 3D perception. In particular, we propose a novel 3D backbone, WaffleIron, made almost exclusively of MLPs and dense 2D convolutions and present how to train it to reach high performance on SemanticKITTI and nuScenes. We believe that WaffleIron is a compelling alternative to backbones using sparse 3D convolutions, especially in frameworks and on hardware where those convolutions are not readily available. The code is available at https://github.com/valeoai/WaffleIron.

We propose SeedAL, a method to seed active learning for efficient annotation of 3D point clouds for semantic segmentation. Active Learning (AL) iteratively selects relevant data fractions to annotate within a given budget, but requires a first fraction of the dataset (a ’seed’) to be already annotated to estimate the benefit of annotating other data fractions. We first show that the choice of the seed can significantly affect the performance of many AL methods. We then propose a method for automatically constructing a seed that will ensure good performance for AL. Assuming that images of the point clouds are available, which is common, our method relies on powerful unsupervised image features to measure the diversity of the point clouds. It selects the point clouds for the seed by optimizing the diversity under an annotation budget, which can be done by solving a linear optimization problem. Our experiments demonstrate the effectiveness of our approach compared to random seeding and existing methods on both the S3DIS and SemanticKitti datasets. Code is available at https://github.com/nerminsamet/seedal.

We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient object over the input sequence. It only relies on independent image features and optical flows, which can be obtained using off-the-shelf self-supervised methods. It scales with the length of the sequence with no need for superpixels or sparsification, and it generalizes to different datasets without any specific training. This objective function can actually be derived from a form of spectral clustering applied to the entire video. Our method achieves on-par performance with the state of the art on standard bench-marks (DAVIS2016, SegTrack-v2, FBMS59), while being conceptually and practically much simpler.

Detecting objects and estimating their viewpoints in images are key tasks of 3D scene understanding. Recent approaches have achieved excellent results on very large benchmarks for object detection and viewpoint estimation. However, performances are still lagging behind for novel object categories with few samples. In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation. We demonstrate on both tasks the benefits of guiding the network prediction with class-representative features extracted from data in different modalities: image patches for object detection, and aligned 3D models for viewpoint estimation. Despite its simplicity, our method outperforms state-of-the-art methods by a large margin on a range of datasets, including PASCAL and COCO for few-shot object detection, and Pascal3D+ and ObjectNet3D for few-shot viewpoint estimation. Furthermore, when the 3D model is not available, we introduce a simple category-agnostic viewpoint estimation method by exploiting geometrical similarities and consistent pose labeling across different classes. While it moderately reduces performance, this approach still obtains better results than previous methods in this setting. Last, for the first time, we tackle the combination of both few-shot tasks, on three challenging benchmarks for viewpoint estimation in the wild, ObjectNet3D, Pascal3D+ and Pix3D, showing very promising results.

Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they lose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO.

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pretraining method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The keyingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks.

3D scene reconstruction has important applications to help to produce digital twins of existing buildings. While the community has mostly focused on surface reconstruction or semantic segmentation as separate problems, the joint reconstruction of both volumes and semantics has little been discussed, mostly due to the lack of large scale volume datasets with semantic annotations. In this work, we introduce a new dataset called VASAD for Volume And Semantic Architectural Dataset. It is composed of 6 building models, with full volume description and semantic labels. It approximately represents 62,000 m2of building floors, making it large enough for the development and evaluation of learning-based approaches. We propose several methods to jointly reconstruct both geometry and semantics and evaluate on the test set of the dataset. We show that the proposed dataset is challenging enough to stimulate research. The dataset is available at https://github.com/palanglois/vasad.

Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface orientation. In this paper, we present two simple ways to augment point clouds with visibility information, so it can directly be leveraged by surface reconstruction networks with minimal adaptation. Our proposed modifications consistently improve the accuracy of generated surfaces as well as the generalization capability of the networks to unseen domains. Our code, data and pretrained models can be found online: https://github.com/raphaelsulzer/dsrv-data.

There has been recently a growing interest for implicit shape representations. Contrary to explicit representations, they have no resolution limitations and they easily deal with a wide variety of surface topologies. To learn these implicit representations, current approaches rely on a certain level of shape supervision (e.g., inside/outside information or distance-to-shape knowledge), or at least require a dense point cloud (to approximate well enough the distance-to-shape). In contrast, we introduce NeeDrop, an self-supervised method for learning shape representations from possibly extremely sparse point clouds. Like in Buffon’s needle problem, we “drop” (sample) needles on the point cloud and consider that, statistically, close to the surface, the needle end points lie on opposite sides of the surface. No shape knowledge is required and the point cloud can be highly sparse, e.g., as lidar point clouds acquired by vehicles. Previous self-supervised shape representation approaches fail to produce good-quality results on this kind of data. We obtain quantitative results on par with existing supervised approaches on shape reconstruction datasets and show promising qualitative results on hard autonomous driving datasets such as KITTI.

While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification. We present the first generative approach for both ZSL and Generalized ZSL (GZSL) on 3D data, that can handle both classification and, for the first time, semantic segmentation. We show that it reaches or outperforms the state of the art on ModelNet40 classification for both inductive ZSL and inductive GZSL. For semantic segmentation, we created three benchmarks for evaluating this new ZSL task, using S3DIS, ScanNet and SemanticKITTI. Our experiments show that our method outperforms strong baselines, which we additionally propose for this task.

Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without CAD model knowledge. The idea is to leverage features learned on seen classes to estimate the pose for classes that are unseen, yet that share similar geometries and canonical frames with seen classes. We train a direct pose estimator in a class-agnostic way by sharing weights across all object classes, and we introduce a contrastive learning method that has three main ingredients: (i) the use of pre-trained, self-supervised, contrast-based features; (ii) pose-aware data augmentations; (iii) a pose-aware contrastive loss. We experimented on Pascal3D+, ObjectNet3D and Pix3D in a cross-dataset fashion, with both seen and unseen classes. We report state-of-the-art results, including against methods that additionally use CAD models as input.

Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of crossattention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets.

We introduce an approach for computing a 3D mesh from one or more views of an object by establishing dense correspondences between pixels in the views and 3D locations on a learnable parameterized surface. We propose a multi-view shape encoder that can be jointly trained with the AtlasNet surface parameterization. The shape is further refined using a novel geometric cycle-consistency loss between the learnable parameterized surface and input views. We demonstrate the efficacy of our approach on the ShapeNet-COCO dataset.

Abstract We introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real‐life Multi‐View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line‐of‐sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real‐life acquisitions. Combining the efficiency of deep learning methods and the scalability of energy‐based models, our approach outperforms both learning and non learning‐based reconstruction algorithms on two publicly available reconstruction benchmarks.

We present an algorithm for extracting and vectorizing objects in images with polygons. Departing from a polygonal partition that oversegments an image into convex cells, the algorithm refines the geometry of the partition while labeling its cells by a semantic class. The result is a set of polygons, each capturing an object in the image. The quality of a configuration is measured by an energy that accounts for both the fidelity to input data and the complexity of the output polygons. To efficiently explore the configuration space, we perform splitting and merging operations in tandem on the cells of the polygonal partition. The exploration mechanism is controlled by a priority queue that sorts the operations most likely to decrease the energy. We show the potential of our algorithm on different types of scenes, from organic shapes to man-made objects through floor maps, and demonstrate its efficiency compared to existing vectorization methods.

In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.

This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

Usual Structure-from-Motion (SfM) techniques require at least trifocal overlaps to calibrate cameras and reconstruct a scene. We consider here scenarios of reduced image sets with little overlap, possibly as low as two images at most seeing the same part of the scene. We propose a new method, based on line coplanarity hypotheses, for estimating the relative scale of two independent bifocal calibrations sharing a camera, without the need of any trifocal information or Manhattan-world assumption. We use it to compute SfM in a chain of up-to-scale relative motions. For accuracy, we however also make use of trifocal information for line and/or point features, when present, relaxing usual trifocal constraints. For robustness to wrong assumptions and mismatches, we embed all constraints in a parameterless RANSAC-like approach. Experiments show that we can calibrate datasets that previously could not, and that this wider applicability does not come at the cost of inaccuracy.

In this paper, we address the problem of Multi-View Stereo (MVS) reconstruction of highly regular man-made scenes from calibrated, wide-baseline views and a sparse Structure-from-Motion (SfM) point cloud. We introduce a novel patch-based formulation via energy minimization which combines top-down segmentation hypotheses using appearance and vanishing line detections, as well as an arrangement of creased planar structures which are extracted automatically through a robust analysis of available SfM points and image features. The method produces a compact piecewise-planar depth map and a mesh which are aligned with the scene's structure. Experiments show that our approach not only reaches similar levels of accuracy w.r.t state-of-the-art pixel-based methods while using much fewer images, but also produces a much more compact, structure-aware mesh in a considerably shorter runtime by several of orders of magnitude.

We propose a multiscale extension of a well-known line segment detector, LSD. We show that its multiscale nature makes it much less prone to over-segmentation, more robust to low contrast and less sensitive to noise, while keeping the parameterless advantage of LSD and still being fast. Moreover, we show that in scenes with little or no feature points, but where it is however possible to perform structure from motion from matched line segments, the accuracy is significantly improved. This provides an objective and automatic quantitative assessment of our detector that goes much beyond the usual qualitative visual inspection found in the literature.

Abstract Normal estimation in point clouds is a crucial first step for numerous algorithms, from surface reconstruction and scene understanding to rendering. A recurrent issue when estimating normals is to make appropriate decisions close to sharp features, not to smooth edges, or when the sampling density is not uniform, to prevent bias. Rather than resorting to manually‐designed geometric priors, we propose to learn how to make these decisions, using ground‐truth data made from synthetic scenes. For this, we project a discretized Hough space representing normal directions onto a structure amenable to deep learning. The resulting normal estimation method outperforms most of the time the state of the art regarding robustness to outliers, to noise and to point density variation, in the presence of sharp edges, while remaining fast, scaling up to millions of points.

We present a new shape prior formalism for the segmentation of rectified facade images. It combines the simplicity of split grammars with unprecedented expressive power: the capability of encoding simultaneous alignment in two dimensions, facade occlusions and irregular boundaries between facade elements. We formulate the task of finding the most likely image segmentation conforming to a prior of the proposed form as a MAP-MRF problem over a 4-connected pixel grid, and propose an efficient optimization algorithm for solving it. Our method simultaneously segments the visible and occluding objects, and recovers the structure of the occluded facade. We demonstrate state-of-the-art results on a number of facade segmentation datasets.

Surface reconstruction from point clouds often relies on a primitive extraction step, that may be followed by a merging step because of a possible over-segmentation. We present two statistical criteria to decide whether or not two surfaces are to be considered as the same, and thus can be merged. They are based on the statistical tests of Kolmogorov-Smirnov and Mann-Whitney for comparing distributions. Moreover, computation time can be significantly cut down using a reduced sampling based on the Dvoretzky-Keifer-Wolfowitz inequality. The strength of our approach is that it relies in practice on a single intuitive parameter (homogeneous to a distance) and that it can be applied to any shape, including meshes, not just geometric primitives. It also enables the comparison of shapes of different kinds, providing a way to choose between different shape candidates. We show several applications of our method, experimenting geometric primitive (plane and cylinder) detection, selection and fusion, both on precise laser scans and noisy photogrammetric 3D data.

Existing approaches to parsing images of objects featuring complex, non-hierarchical structure rely on exploration of a large search space combining the structure of the object and positions of its parts. The latter task requires randomized or greedy algorithms that do not produce repeatable results or strongly depend on the initial solution. To address the problem we propose to model and optimize the structure of the object and position of its parts separately. We encode the possible object structures in a graph grammar. Then, for a given structure, the positions of the parts are inferred using standard MAP-MRF techniques. This way we limit the application of the less reliable greedy or randomized optimization algorithm to structure inference. We apply our method to parsing images of building facades. The results of our experiments compare favorably to the state of the art.

Abstract This paper presents a method for the 3D reconstruction of a piecewise‐planar surface from range images, typically laser scans with millions of points. The reconstructed surface is a watertight polygonal mesh that conforms to observations at a given scale in the visible planar parts of the scene, and that is plausible in hidden parts. We formulate surface reconstruction as a discrete optimization problem based on detected and hypothesized planes. One of our major contributions, besides a treatment of data anisotropy and novel surface hypotheses, is a regularization of the reconstructed surface w.r.t. the length of edges and the number of corners. Compared to classical area‐based regularization, it better captures surface complexity and is therefore better suited for man‐made environments, such as buildings. To handle the underlying higher‐order potentials, that are problematic for MRF optimizers, we formulate minimization as a sparse mixed‐integer linear programming problem and obtain an approximate solution using a simple relaxation. Experiments show that it is fast and reaches near‐optimal solutions.

Multi-view structure from motion (SfM) estimates the position and orientation of pictures in a common 3D coordinate frame. When views are treated incrementally, this external calibration can be subject to drift, contrary to global methods that distribute residual errors evenly. We propose a new global calibration approach based on the fusion of relative motions between image pairs. We improve an existing method for robustly computing global rotations. We present an efficient a contrario trifocal tensor estimation method, from which stable and precise translation directions can be extracted. We also define an efficient translation registration method that recovers accurate camera positions. These components are combined into an original SfM pipeline. Our experiments show that, on most datasets, it outperforms in accuracy other existing incremental and global pipelines. It also achieves strikingly good running times: it is about 20 times faster than the other global method we could compare to, and as fast as the best incremental method. More importantly, it features better scalability properties.

Abstract We propose a new approach to automatically semantize complex objects in a 3D scene. For this, we define an expressive formalism combining the power of both attribute grammars and constraint. It offers a practical conceptual interface, which is crucial to write large maintainable specifications. As recursion is inadequate to express large collections of items, we introduce maximal operators, that are essential to reduce the parsing search space. Given a grammar in this formalism and a 3D scene, we show how to automatically compute a shared parse forest of all interpretations — in practice, only a few, thanks to relevant constraints. We evaluate this technique for building model semantization using CAD model examples as well as photogrammetric and simulated LiDAR data.

Finding reliable correspondences between sets of feature points in two images remains challenging in case of ambiguities or strong transformations. In this paper, we define a photometric descriptor for virtual lines that join neighbouring feature points. We show that it can be used in the second-order term of existing graph matchers to significantly improve their accuracy. We also define a semi-local matching method based on this descriptor. We show that it is robust to strong transformations and more accurate than existing graph matchers for scenes with significant occlusions, including for very low inlier rates. Used as a preprocessor to filter outliers from match candidates, it significantly improves the robustness of RANSAC and reduces camera calibration errors.

Abstract This paper presents a new method for estimating normals on unorganized point clouds that preserves sharp features. It is based on a robust version of the Randomized Hough Transform (RHT). We consider the filled Hough transform accumulator as an image of the discrete probability distribution of possible normals. The normals we estimate corresponds to the maximum of this distribution. We use a fixed‐size accumulator for speed, statistical exploration bounds for robustness, and randomized accumulators to prevent discretization effects. We also propose various sampling strategies to deal with anisotropy, as produced by laser scans due to differences of incidence. Our experiments show that our approach offers an ideal compromise between precision, speed, and robustness: it is at least as precise and noise‐resistant as state‐of‐the‐art methods that preserve sharp features, while being almost an order of magnitude faster. Besides, it can handle anisotropy with minor speed and precision losses.

Specialization has been recognized as a powerful technique for optimizing operating systems. However, specialization has not been broadly applied beyond the research community because current techniques based on manual specialization, are time-consuming and error-prone. The goal of the work described in this paper is to help operating system tuners perform specialization more easily. We have built a specialization toolkit that assists the major tasks of specializing operating systems. We demonstrate the effectiveness of the toolkit by applying it to three diverse operating system components. We show that using tools to assist specialization enables significant performance optimizations without error-prone manual modifications. Our experience with the toolkit suggests new ways of designing systems that combine high performance and clean structure.

An adaptive component is a component that is able to adapt its behavior to different execution contexts. Building an adaptive application is difficult because of component dependencies and the lack of language support. As a result, code that implements adaptation is often tangled, hindering maintenance and evolution. To overcome this problem, we propose a declarative approach to program adaptation. This approach makes the specific issues of adaptation explicit. The programmer can focus on the basic features of the application, and separately provide clear and concise adaptation information. Concretely, we propose adaptation classes, which enrich Java classes with adaptive behaviors. A dedicated compiler automatically generates Java code that implements the adaptive features. Moreover, these adaptation declarations can be checked for consistency to provide additional safety guarantees. As a working example throughout this paper, we use an adaptive sound encoder in an audio-conferencing application. We show the problems associated with a traditional implementation using design patterns, and how these problems are elegantly solved using adaptation classes.

Although new peripheral devices are emerging at a frantic pace and require the fast release of drivers, little progress has been made to improve the development of such device drivers. Too often, this development consists of decoding hardware intricacies, based on inaccurate documentation. Then, assembly-level operations need to be used to interact with the device. These low-level operations reduce the readability of the driver and prevent safety properties from being checked. This paper presents an approach based on domain-specific languages (DSLs) to overcome these problems. We define a language, named Devil (DEVice Interaction Language), dedicated to defining the basic communication with a device. Unlike a general-purpose language, Devil allows a description to be checked for consistency. This not only improves the safety of the interaction with the device but also uncovers bugs early in the development process. To asses our approach, we have shown that Devil is expressive enough to specify a large number of devices. To evaluate productivity and safety improvements over traditional development in C, we report an experiment based on mutation testing.

Availability of data in a program determines computation stages. Incremental partial evaluation exploit these stages for optimization: it allows further specialization to be performed as data become available at later stages. The fundamental advantage of incremental specialization is to factorize the specialization process. As a result, specializing a program at a given stage costs considerably less than specializing it once all the data are available.We present a realistic and flexible approach to achieve efficient incremental run-time specialization. Rather than developing specific techniques, as previously proposed, we are able to re-use existing technology by iterating a specialization process. Moreover, in doing so, we do not lose any specialization opportunities. This approach makes it possible to exploit nested quasi-invariants and to speed up the run-time specialization process.This approach has been implemented in Tempo, a specializer for C programs that is publicly available. A preliminary experiment confirm that incremental that incremental specialization can greatly speed up the specialization process.

Domain-specific languages (DSL) have many potential advantages in terms of software engineering, ranging from increased productivity to the application of formal methods. Although they have been used in practice for decades, there has been little study of methodology or implementation tools for the DSL approach. We present our DSL approach and its application to a realistic domain: the generation of video display device drivers. The article focuses on the validation of our proposed framework for domain-specific languages, from design to implementation. The framework leads to a flexible design and structure, and provides automatic generation of efficient implementations of DSL programs. Additionally, we describe an example of a complete DSL for video display adaptors and the benefits of the DSL approach for this application. This demonstrates some of the generally claimed benefits of using DSLs: increased productivity, higher-level abstraction, and easier verification. This DSL has been fully implemented with our approach and is available. Compose project URL: http://www.irisa.fr/compose/gal.

Fast remote procedure call (RPC) is a major concern for distributed systems. Many studies aimed at efficient RPC consist of either new implementations of the RPC paradigm or manual optimization of critical sections of the code. This paper presents an experiment that achieves automatic optimization of an existing, commercial RPC implementation, namely the Sun RPC. The optimized Sun RPC is obtained by using an automatic program specializer. It runs up to 1.5 times faster than the original Sun RPC. Close examination of the specialized code does not reveal further optimization opportunities which would lead to significant improvements without major manual restructuring. The contributions of this work are: the optimized code is safely produced by an automatic tool and thus does not entail any additional maintenance; to the best of our knowledge this is the first successful specialization of mature, commercial, representative system code; and the optimized Sun RPC runs significantly faster than the original code.

Flexibility is recognized as a key feature in structuring software, and many architectures have been designed to that effect. However, they often come with performance and code size overhead, resulting in a flexibility vs. efficiency dilemma. The source of inefficiency in software architectures can be identified in the data and control integration of components, because flexibility is present not only at the design level but also in the implementation. We propose the use of program specialization in software engineering as a systematic way to improve performance and in some cases, to reduce program size. In particular, we advocate the use of partial evaluation, which is an automatic technique to produce efficient, specialized instances of generic programs. We study several representative, flexible mechanisms found in software architectures: selective broadcast, pattern matching, interpreters, layers, and generic libraries. We show how partial evaluation can systematically be applied in order to optimize those mechanisms.

We report here a successful experiment in using partial evaluation on a realistic program, namely the Sun commercial RPC (Remote Procedure Call) protocol. The Sun RPC is implemented in a highly generic way that offers multiple opportunities of specialization.Our study also shows the incapacity of traditional binding-time analyses to treat real system programs. Our experiment has been made with Tempo, a partial evaluator for C programs targeted towards system software. Tempo's binding-time analysis had to be improved to integrate partially static data structures (interprocedurally), context sensitivity, use sensitivity and return sensitivity.The Sun RPC experiment files, including the specialized implementation, are publicly available upon request to the authors.