Luis Roldão
Research Subjects
Luis Roldão has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Dzmitry Tsishkou
Noah’s Ark, Huawei Paris Research Center
7 shared publications - Moussab Bennehar
Noah’s Ark, Huawei Paris Research Center
7 shared publications - Nathan Piasco
Noah’s Ark, Huawei Paris Research Center
7 shared publications - Anne Verroust-Blondet
Inria Paris France
3 shared publications - Raoul de Charette
INRIA
3 shared publications - Cédric Demonceaux
Université Bourgogne Europe, CNRS, ICB UMR 6303
2 shared publications
Latest Publications
- 4 October 2026
- Published by Springer Nature
- p. 221-238
LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding
- 4 October 2026
- Published by Springer Nature
- p. 221-238
LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding
- 4 October 2026
- Published by Springer Nature
- p. 512-529
SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
- 4 October 2026
- Published by Springer Nature
- p. 512-529
SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
- 3 November 2024
- Published by Springer Nature
- p. 112-130
RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes
- 3 November 2024
- Published by Springer Nature
- p. 112-130
RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes
- 31 October 2024
- Published by Springer Nature
- p. 325-340
SWAG: Splatting in the Wild Images with Appearance-Conditioned Gaussians
- 31 October 2024
- Published by Springer Nature
- p. 325-340
SWAG: Splatting in the Wild Images with Appearance-Conditioned Gaussians
- Open Access
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.
Open AccessSOAC: 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.
- Open Access
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.
Open AccessPlaNeRF: 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.
- Open Access
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.
Open AccessMOISST: 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.
- 6 June 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (8) , 1978-2005
3D Semantic Scene Completion: A Survey
- 6 June 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (8) , 1978-2005
3D Semantic Scene Completion: A Survey
- Open Access
3D Semantic Scene Completion: a Survey
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum in the research community because it holds unresolved challenges. Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. This led to a substantially increasing number of papers on the matter. This survey aims to identify, compare and analyze the techniques providing a critical analysis of the SSC literature on both methods and datasets. Throughout the paper, we provide an in-depth analysis of the existing works covering all choices made by the authors while highlighting the remaining avenues of research. SSC performance of the SoA on the most popular datasets is also evaluated and analyzed.
Open Access3D Semantic Scene Completion: a Survey
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum in the research community because it holds unresolved challenges. Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. This led to a substantially increasing number of papers on the matter. This survey aims to identify, compare and analyze the techniques providing a critical analysis of the SSC literature on both methods and datasets. Throughout the paper, we provide an in-depth analysis of the existing works covering all choices made by the authors while highlighting the remaining avenues of research. SSC performance of the SoA on the most popular datasets is also evaluated and analyzed.
- Open Access
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.
Open AccessLMSCNet: 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.