arXiv subjects

Luis Roldão

Publications and source records attributed to Luis Roldão.

18 recordsLinked to original sources

arXiv2026

Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering

Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccuracies in sensor calibration and ego-poses can silently degrade both model performance and evaluation reliability. We introduce MOISST++, a Neural Radiance Field (NeRF)-based pipeline that jointly refines extrinsic sensor calibration and continuous-time ego-trajectories at dataset scale. The method optimizes shared rig parameters across multiple subsequences and corrects per-subsequence trajectories via a learned continuous-time correction, going beyond prior work that targets individual scenes. We validate pose improvements without ground truth through a complementary evaluation suite combining Structure from Motion (SfM) triangulation, novel view synthesis, and multi-modal geometric consistency metrics, verify their coherence via cross-metric agreement, and confirm their sensitivity through a controlled-perturbation study with known injected errors. Applied to four major datasets (KITTI-360, nuScenes, PandaSet, and Waymo), MOISST++ yields statistically significant improvements on most metrics on nuScenes, PandaSet and Waymo, and marginal, within-noise changes on the already well-calibrated KITTI-360. We publicly release the optimized poses and calibration parameters, together with our evaluation code, to support more reliable research and benchmarking.

cs.CV↗

arXiv2026

HELIOS: From midnight to noon, continuous outdoor urban scene relighting

Modifying the illumination of driving images is a fundamental challenge, as most datasets are captured at specific times of day. Existing methods rely on synthetic data or paired multi-illumination supervision, which limits their generalization to the diverse and challenging conditions of real-world scenarios. To address this, we propose HELIOS, a novel image relighting approach that relies on unlabeled real-world datasets without requiring any paired images for training. Our approach integrates albedo-based conditioning into a cycle-consistent diffusion pipeline to prevent identity collapse and ensure accurate domain translation. To handle low-visibility nighttime conditions, we introduce a robust albedo distillation strategy that transfers structural stability from the daytime domain. Additionally, we replace traditional text prompts with a fine-grained control mechanism based on GPS-derived solar angles, enabling smooth and continuous lighting manipulation across the day-night cycle. Through extensive evaluation and a user study, we demonstrate that HELIOS produces structurally consistent and realistic results in both night-to-day and day-to-night tasks, outperforming state-of-the-art methods.

cs.CV↗

arXiv2026

LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding

Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial ambiguity arising from unstructured, overlapping Gaussians which necessitates probabilistic feature registration, and the multi-level semantic ambiguity caused by pooling features over object-level masks, which dilutes fine-grained details. To address these challenges, we present a novel framework that leverages Sparse Voxel Rasterization (SVRaster) as a structured, disjoint geometry representation. By regularizing SVRaster with monocular depth and normal priors, we establish a stable geometric foundation. This enables a deterministic, confidence-aware feature registration process and suppresses the semantic bleeding artifact common in 3DGS. Furthermore, we resolve multi-level ambiguity by exploiting the emerging dense alignment properties of the AM-RADIO foundation model, avoiding the computational overhead of hierarchical training methods. Our approach achieves state-of-the-art performance on Open Vocabulary Point Cloud Understanding, and highly competitive results on 3D and 2D Object Retrieval benchmarks.

cs.CV↗

arXiv2026

DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction

Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects. Currently, potentially faster sparse voxel methods are mainly designed for static scenarios. On the other hand, dynamic approaches based on 3D Gaussian Splatting, despite their high-fidelity, are often time-consuming for driving scenarios and exhibit uncontrollable memory growth in large scenes. To address these limitations, we present DrivingVoxels, a compositional sparse voxel rendering framework for dynamic driving scenes. Our method jointly rasterizes sparse voxels from multiple independent octrees within a single rendering pass. Each rigid dynamic object is represented by an octree defined in its local coordinate frame, while a separate static octree models the stationary background. DrivingVoxels adopts a fully explicit, neural-free representation together with a LiDAR-guided structural initialization that efficiently captures scene geometry. We evaluate our framework on the PandaSet benchmark, demonstrating that DrivingVoxels performs on par on perceptual metrics and better on structural metrics for NVS and reconstruction while requiring shorter training times than previous 3DGS-base methods to an efficient optimization workflow anchored by a strong LiDAR prior.

cs.CV↗

arXiv2026

SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation

Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing solutions either rely on image or video generative models distilled to 3D space, harming the geometric coherence and restricting the rendering to training views, or are limited to small-scale 3D scene or object-centric generation. In this work, we propose a 3D generative framework based on $Σ$-Voxfield grid, a discrete representation where each occupied voxel stores a fixed number of colorized surface samples. To generate this representation, we train a semantic-conditioned diffusion model that operates on local voxel neighborhoods and uses 3D positional encodings to capture spatial structure. We scale to large scenes via progressive spatial outpainting over overlapping regions. Finally, we render the generated $Σ$-Voxfield grid with a deferred rendering module to obtain photorealistic images, enabling large-scale multiview-consistent 3D scene generation without per-scene optimization. Extensive experiments show that our approach can generate diverse large-scale urban outdoor scenes, renderable into photorealistic images with various sensor configurations and camera trajectories while maintaining moderate computation cost compared to existing approaches.

cs.CV↗

arXiv2025

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis

Synthesizing extrapolated views remains a difficult task, especially in urban driving scenes, where the only reliable sources of data are limited RGB captures and sparse LiDAR points. To address this problem, we present PointmapDiff, a framework for novel view synthesis that utilizes pre-trained 2D diffusion models. Our method leverages point maps (i.e., rasterized 3D scene coordinates) as a conditioning signal, capturing geometric and photometric priors from the reference images to guide the image generation process. With the proposed reference attention layers and ControlNet for point map features, PointmapDiff can generate accurate and consistent results across varying viewpoints while respecting geometric fidelity. Experiments on real-life driving data demonstrate that our method achieves high-quality generation with flexibility over point map conditioning signals (e.g., dense depth map or even sparse LiDAR points) and can be used to distill to 3D representations such as 3D Gaussian Splatting for improving view extrapolation.

cs.CV↗

arXiv2025

J-NeuS: Joint field optimization for Neural Surface reconstruction in urban scenes with limited image overlap

Reconstructing the surrounding surface geometry from recorded driving sequences poses a significant challenge due to the limited image overlap and complex topology of urban environments. SoTA neural implicit surface reconstruction methods often struggle in such setting, either failing due to small vision overlap or exhibiting suboptimal performance in accurately reconstructing both the surface and fine structures. To address these limitations, we introduce J-NeuS, a novel hybrid implicit surface reconstruction method for large driving sequences with outward facing camera poses. J-NeuS cross-representation uncertainty estimation to tackle ambiguous geometry caused by limited observations. Our method performs joint optimization of two radiance fields in addition to guided sampling achieving accurate reconstruction of large areas along with fine structures in complex urban scenarios. Extensive evaluation on major driving datasets demonstrates the superiority of our approach in reconstructing large driving sequences with limited image overlap, outperforming concurrent SoTA methods.

cs.CV↗

arXiv2025

SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model

Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting and scene editing. Despite the rise and success of learning-based approaches, intrinsic image decomposition from real-world images remains a significant challenging task due to the scarcity of labeled ground-truth data. Most existing solutions rely on synthetic data as supervised setups, limiting their ability to generalize to real-world scenes. Self-supervised methods, on the other hand, often produce albedo maps that contain reflections and lack consistency under different lighting conditions. To address this, we propose SAIL, an approach designed to estimate albedo-like representations from single-view real-world images. We repurpose the prior knowledge of a latent diffusion model for unconditioned scene relighting as a surrogate objective for albedo estimation. To extract the albedo, we introduce a novel intrinsic image decomposition fully formulated in the latent space. To guide the training of our latent diffusion model, we introduce regularization terms that constrain both the lighting-dependent and independent components of our latent image decomposition. SAIL predicts stable albedo under varying lighting conditions and generalizes to multiple scenes, using only unlabeled multi-illumination data available online.

cs.CV↗

arXiv2025

ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap

Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and their limited visual observation overlap. Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required. To tackle such limitations, we present ViiNeuS, a new hybrid implicit surface learning method that efficiently initializes the signed distance field to reconstruct large driving scenes from 2D street view images. ViiNeuS's hybrid architecture models two separate implicit fields: one representing the volumetric density of the scene, and another one representing the signed distance to the surface. To accurately reconstruct urban outdoor driving scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods. By conducting extensive experiments on four outdoor driving datasets, we show that ViiNeuS can learn an accurate and detailed 3D surface representation of various urban scene while being two times faster to train compared to previous state-of-the-art solutions.

cs.CV↗

arXiv2024

RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes

The task of separating dynamic objects from static environments using NeRFs has been widely studied in recent years. However, capturing large-scale scenes still poses a challenge due to their complex geometric structures and unconstrained dynamics. Without the help of 3D motion cues, previous methods often require simplified setups with slow camera motion and only a few/single dynamic actors, leading to suboptimal solutions in most urban setups. To overcome such limitations, we present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes, with thoughtfully separated NeRF models for moving and non-moving components. Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process. This strategy enables accurate capturing of the dynamics in the scene, resulting in reduced floating artifacts in the reconstructed background, all by using self-supervision. Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components.

cs.CV↗

arXiv2024

SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields

In rapidly-evolving domains such as autonomous driving, the use of multiple sensors with different modalities is crucial to ensure high operational precision and stability. To correctly exploit the provided information by each sensor in a single common frame, it is essential for these sensors to be accurately calibrated. In this paper, we leverage the ability of Neural Radiance Fields (NeRF) to represent different sensors modalities in a common volumetric representation to achieve robust and accurate spatio-temporal sensor calibration. By designing a partitioning approach based on the visible part of the scene for each sensor, we formulate the calibration problem using only the overlapping areas. This strategy results in a more robust and accurate calibration that is less prone to failure. We demonstrate that our approach works on outdoor urban scenes by validating it on multiple established driving datasets. Results show that our method is able to get better accuracy and robustness compared to existing methods.

cs.CV↗

arXiv2023

PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction

Neural Radiance Fields (NeRF) enable 3D scene reconstruction from 2D images and camera poses for Novel View Synthesis (NVS). Although NeRF can produce photorealistic results, it often suffers from overfitting to training views, leading to poor geometry reconstruction, especially in low-texture areas. This limitation restricts many important applications which require accurate geometry, such as extrapolated NVS, HD mapping and scene editing. To address this limitation, we propose a new method to improve NeRF's 3D structure using only RGB images and semantic maps. Our approach introduces a novel plane regularization based on Singular Value Decomposition (SVD), that does not rely on any geometric prior. In addition, we leverage the Structural Similarity Index Measure (SSIM) in our loss design to properly initialize the volumetric representation of NeRF. Quantitative and qualitative results show that our method outperforms popular regularization approaches in accurate geometry reconstruction for large-scale outdoor scenes and achieves SoTA rendering quality on the KITTI-360 NVS benchmark.

cs.CV↗

arXiv2023

MOISST: Multimodal Optimization of Implicit Scene for SpatioTemporal calibration

With the recent advances in autonomous driving and the decreasing cost of LiDARs, the use of multimodal sensor systems is on the rise. However, in order to make use of the information provided by a variety of complimentary sensors, it is necessary to accurately calibrate them. We take advantage of recent advances in computer graphics and implicit volumetric scene representation to tackle the problem of multi-sensor spatial and temporal calibration. Thanks to a new formulation of the Neural Radiance Field (NeRF) optimization, we are able to jointly optimize calibration parameters along with scene representation based on radiometric and geometric measurements. Our method enables accurate and robust calibration from data captured in uncontrolled and unstructured urban environments, making our solution more scalable than existing calibration solutions. We demonstrate the accuracy and robustness of our method in urban scenes typically encountered in autonomous driving scenarios.

cs.CV↗

arXiv2020

LMSCNet: Lightweight Multiscale 3D Semantic Completion

We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow, along with 3D segmentation heads. On the SemanticKITTI benchmark, our method performs on par on semantic completion and better on occupancy completion than all other published methods -- while being significantly lighter and faster. As such it provides a great performance/speed trade-off for mobile-robotics applications. The ablation studies demonstrate our method is robust to lower density inputs, and that it enables very high speed semantic completion at the coarsest level. Our code is available at https://github.com/cv-rits/LMSCNet.

cs.CV↗

arXiv2020

Description and Technical specification of Cybernetic Transportation Systems: an urban transportation concept

The Cybernetic Transportation Systems (CTS) is an urban mobility concept based on two ideas: the car sharing and the automation of dedicated systems with door-to-door capabilities. In the last decade, many European projects have been developed in this context, where some of the most important are: Cybercars, Cybercars2, CyberMove, CyberC3 and CityMobil. Different companies have developed a first fleet of CTSs in collaboration with research centers around Europe, Asia and America. Considering these previous works, the FP7 project CityMobil2 is on progress since 2012. Its goal is to solve some of the limitations found so far, including the definition of the legal framework for autonomous vehicles on urban environment. This work describes the different improvements, adaptation and instrumentation of the CTS prototypes involved in European cities. Results show tests in our facilities at INRIA-Rocquencourt (France) and the first showcase at León (Spain)

cs.RO↗

arXiv2019

Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps

Lidar has become an essential sensor for autonomous driving as it provides reliable depth estimation. Lidar is also the primary sensor used in building 3D maps which can be used even in the case of low-cost systems which do not use Lidar. Computation on Lidar point clouds is intensive as it requires processing of millions of points per second. Additionally there are many subsequent tasks such as clustering, detection, tracking and classification which makes real-time execution challenging. In this paper, we discuss real-time dynamic object detection algorithms which leverages previously mapped Lidar point clouds to reduce processing. The prior 3D maps provide a static background model and we formulate dynamic object detection as a background subtraction problem. Computation and modeling challenges in the mapping and online execution pipeline are described. We propose a rejection cascade architecture to subtract road regions and other 3D regions separately. We implemented an initial version of our proposed algorithm and evaluated the accuracy on CARLA simulator.

cs.CV↗

arXiv2019

A Statistical Update of Grid Representations from Range Sensors

In a wide range of robotic applications, being able to create a 3D model of the surrounding environment is a key feature for autonomous tasks. In this research report, we present a statistical model to perform 3D reconstructions of the environment from range sensors using an occupancy grid. To do so, we take into account all the available information obtained from the sensor, considering the distances traversed by the rays in each cell and seeking to reduce reconstruction errors caused by discretization. The approach has been validated qualitatively using the KITTI dataset.

cs.RO↗

arXiv2019

3D Surface Reconstruction from Voxel-based Lidar Data

To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is based on a TSDF voxel-based representation, where an adaptive neighborhood kernel sourced on a Gaussian confidence evaluation is introduced. This enables to keep a good trade-off between the density of the reconstructed mesh and its accuracy. Experimental evaluations carried on both synthetic (CARLA) and real (KITTI) 3D data show a good performance compared to a state of the art method used for surface reconstruction.

cs.CV↗