Renaud Marlet

École des Ponts ParisTech (ENPC), France · Laboratoire d'Informatique Gaspard-Monge (LIGM)

A common strategy to improve lidar segmentation results on rare semantic classes consists of pasting objects from one lidar scene into another. While this augments the quantity of instances seen at training time and varies their context, the instances fundamentally remain the same. In this work, we explore how to enhance instance diversity using a...

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 l...

We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to performing domain adaptation on an unlabeled target domain without any access to source data; the available information is a model trained to achieve good performance on the source domain. A common issue with existing...

Annotating lidar point clouds for autonomous driving is a notoriously expensive and time-consuming task. In this work, we show that the quality of recent self-supervised lidar scan representations allows a great reduction of the annotation cost. Our method has two main steps. First, we show that self-supervised representations allow a simple and di...

Recent VLMs, pre-trained on large amounts of image-text pairs to align both modalities, have opened the way to open-vocabulary semantic segmentation. Given an arbitrary set of textual queries, image regions are assigned the closest query in feature space. However, the usual setup expects the user to list all possible visual concepts that may occur...

Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect from sensor data (cameras or LiDARs) the position and past trajectories of the different elements of the scene and predic...

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 h...

We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE. We show that diffusion models enhance the accuracy, robustness, and coherence of human pose estimations. We introduce DiffHPE, a novel strategy for ha...

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 dat...

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 pape...

We survey and benchmark traditional and novel learning-based algorithms that address the problem of surface reconstruction from point clouds. Surface reconstruction from point clouds is particularly challenging when applied to real-world acquisitions, due to noise, outliers, non-uniform sampling and missing data. Traditionally, different handcrafte...

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...

Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points over large field of views. Today, most deep networks designed for this task exploit 3D sparse convolutions to reduce memory and computational loads. The best methods then further exploit specificities of rotating lidar s...

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 tha...

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to display high loss when evaluated on minority groups not presenting such correlations. Extensive attempts have been...

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. I...

Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface orientation. In this paper, we present two simple ways to augment raw point clouds with visibility information, so it c...

Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet fully understood. This paper introduces a spherical framework to study the optimization of neural networks with NLs from a geometric perspective. Concretely, the radial invariance of groups of...

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 patche...

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 inform...

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...

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...

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner. Our method, LOST, does not require any external object proposal nor any exploration of the...

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 in...

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, semant...

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 in...

Motivated by the need of estimating the pose (viewpoint) of arbitrary objects in the wild, which is only covered by scarce and small datasets, we consider the challenging problem of class-agnostic 3D object pose estimation, with no 3D shape knowledge. The idea is to leverage features learned on seen classes to estimate the pose for classes that are...

Recent state-of-the-art methods for point cloud processing are based on the notion of point convolution, for which several approaches have been proposed. In this paper, inspired by discrete convolution in image processing, we provide a formulation to relate and analyze a number of point convolution methods. We also propose our own convolution varia...

Detecting objects and estimating their viewpoint 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 proble...

We propose and study a method called FLOT that estimates scene flow on point clouds. We start the design of FLOT by noticing that scene flow estimation on point clouds reduces to estimating a permutation matrix in a perfect world. Inspired by recent works on graph matching, we build a method to find these correspondences by borrowing tools from opt...

We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel me...

Detecting objects and estimating their viewpoint 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 proble...

We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel me...

We propose and study a method called FLOT that estimates scene flow on point clouds. We start the design of FLOT by noticing that scene flow estimation on point clouds reduces to estimating a permutation matrix in a perfect world. Inspired by recent works on graph matching, we build a method to find these correspondences by borrowing tools from opt...

Batch Normalization (BN) is a prominent deep learning technique. In spite of its apparent simplicity, its implications over optimization are yet to be fully understood. In this paper, we study the optimization of neural networks with BN layers from a geometric perspective. We leverage the radial invariance of groups of parameters, such as neurons f...

Recent state-of-the-art methods for point cloud semantic segmentation are based on convolution defined for point clouds. In this paper, we propose a formulation of the convolution for point cloud directly designed from the discrete convolution in image processing. The resulting formulation underlines the separation between the discrete kernel space...

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 RANS...

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose. We believe this is a crucial step to design...

This monograph describes the development of Rhapsodie, a 33,000-word syntactic and prosodic treebank of spoken French created with the aim of modeling the interface between prosody, syntax and discourse in spoken French. Theoretical foundations and methodological choices are presented and discussed, and compared with other contemporary approaches....

Localizing an object accurately with respect to a robot is a key step for autonomous robotic manipulation. In this work, we propose to tackle this task knowing only 3D models of the robot and object in the particular case where the scene is viewed from uncalibrated cameras -- a situation which would be typical in an uncontrolled environment, e.g.,...

Localizing an object accurately with respect to a robot is a key step for autonomous robotic manipulation. In this work, we propose to tackle this task knowing only 3D models of the robot and object in the particular case where the scene is viewed from uncalibrated cameras—a situation which would be typical in an uncontrolled environment, e.g., on...

The OpenMVG C++ library provides a vast collection of multiple-view geometry tools and algorithms to spread the usage of computer vision and structure-from-motion techniques. Close to the state-of-the-art in its domain, it provides an easy access to common tools used in 3D reconstruction from images. Following the credo “Keep it simple, keep it mai...

We propose a multiscale extension of a well-known line segment detector, LSD. We show that its multiscale nature makes it much less susceptible to over-segmentation and more robust to low contrast and less sensitive to noise, while keeping the parameter-less advantage of LSD and still being fast. We also present here a dense gradient filter that di...

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...

This work shows how deep learning techniques can benefit to remote sensing. We focus on tasks which are recurrent in Earth Observation data analysis. For classification and semantic mapping of aerial images, we present various deep network architectures and show that context information and dense labeling allow to reach better performances. For est...

Usual Structure from Motion techniques based on feature points have a hard time on scenes with little texture or presenting a single plane, as in indoor environments. Line segments are more robust features in this case. We propose a novel geometrical criterion for two-view pose estimation using lines, that does not assume a Manhattan world. We also...

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a uni...

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 resort...

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 a...

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 a...

Parsing facade images requires optimal handcrafted grammar for a given class of buildings. Such a handcrafted grammar is often designed manually by experts. In this paper, we present a novel framework to learn a compact grammar from a set of ground-truth images. To this end, parse trees of ground-truth annotated images are obtained running existing...

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies that lead a network to learn this representations. The choice of the representation is crucial since the pose of...

We propose a novel formulation for parsing facade images with user-defined shape prior. Contrary to other state-of-the-art methods, we do not explore the procedural space of shapes derived from a grammar. Instead we formulate parsing as a linear binary program which we solve using Dual Decomposition. The algorithm produces plausible approximations...

We present an approach to enhance the accuracy of structure from motion (SfM) in the two-view case. We first answer the question: "fewer data with higher accuracy, or more data with less accuracy?" For this, we establish a relation between SfM errors and a function of the number of matches and their epipolar errors. Using an accuracy estima-tor of...

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 Kolmogoro...

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 s...

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 ad...

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 rel...

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 collection...