Malcolm Mielle

Jean Cordonnier, Chenghao Xu, Olga Fink et al.

Multi-modal novel view synthesis (NVS) combining RGB and thermal imagery enables precise 3D scene reconstruction with visual and thermal information. However, existing methods typically rely on precisely calibrated RGB-thermal image pairs or stereo setups, limiting scalability and practical deployment. To address this, we introduce a framework for unpaired RGB-thermal NVS that leverages VGGT, a 3D feed-forward transformer architecture, to independently estimate camera poses for each modality. The pose sets are then aligned using the Procrustes algorithm with a cross-modal feature matcher, enabling joint registration without paired calibration. Building on this alignment, we further propose a multi-modal 3D Gaussian Splatting approach that learns directly from unpaired RGB and thermal images. Experiments on diverse scenes demonstrate that our method achieves competitive performance in thermal view synthesis while maintaining RGB fidelity. Moreover, we show that existing reconstruction approaches can produce modality-specific reconstructions that lack cross-modal consistency. We thus introduce a benchmarking framework to rigorously evaluate both per-modality image synthesis and the multi-modal coherence of reconstructed scenes.

Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun et al.

Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB datasets. However, their effectiveness drops when applied to mixed sensing modalities, such as RGB-thermal (RGB-T) images. We observe that while a visual geometry grounded transformer pretrained on RGB data generalizes well to thermal-only reconstruction, it struggles to align RGB and thermal modalities when processed jointly. To address this, we propose SEAR, a simple yet efficient fine-tuning strategy that adapts a pretrained geometry transformer to multimodal RGB-T inputs. Despite being trained on a relatively small RGB-T dataset, our approach significantly outperforms state-of-the-art methods for 3D reconstruction and camera pose estimation, achieving significant improvements over all metrics (e.g., over 29\% in AUC@30) and delivering higher detail and consistency between modalities with negligible overhead in inference time compared to the original pretrained model. Notably, SEAR enables reliable multimodal pose estimation and reconstruction even under challenging conditions, such as low lighting and dense smoke. We validate our architecture through extensive ablation studies, demonstrating how the model aligns both modalities. Additionally, we introduce a new dataset featuring RGB and thermal sequences captured at different times, viewpoints, and illumination conditions, providing a robust benchmark for future work in multimodal 3D scene reconstruction. Code and models are publicly available at https://www.github.com/Schindler-EPFL-Lab/SEAR.

Shuo Sun, Unal Artan, Malcolm Mielle et al.

We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches either handle only single-camera input or require rigidly mounted, pre-calibrated camera rigs, limiting their practical applicability. We propose a two-stage optimization framework that decouples the task into robust camera tracking and dense depth refinement. In the first stage, we extend single-camera visual SLAM to the multi-camera setting by constructing a spatiotemporal connection graph that exploits both intra-camera temporal continuity and inter-camera spatial overlap, enabling consistent scale and robust tracking. To ensure robustness under limited overlap, we introduce a wide-baseline initialization strategy using feed-forward reconstruction models. In the second stage, we refine depth and camera poses by optimizing dense inter- and intra-camera consistency using wide-baseline optical flow. Additionally, we introduce MultiCamRobolab, a new real-world dataset with ground-truth poses from a motion capture system. Finally, we demonstrate that our method significantly outperforms state-of-the-art feed-forward models on both synthetic and real-world benchmarks, while requiring less memory.

Leen Daher, Zhaobo Wang, Malcolm Mielle

Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference, limiting deployment in resource-constrained environments where full sensor suites are not economically and technically usable. To address this, we propose Decoupled Cross-Attention Transfer (D-CAT), a framework that aligns modality-specific representations without requiring joint sensor modality during inference. Our approach combines a self-attention module for feature extraction with a novel cross-attention alignment loss, which enforces the alignment of sensors' feature spaces without requiring the coupling of the classification pipelines of both modalities. We evaluate D-CAT on three multi-modal human activity datasets (IMU, video, and audio) under both in-distribution and out-of-distribution scenarios, comparing against uni-modal models. Results show that in in-distribution scenarios, transferring from high-performing modalities (e.g., video to IMU) yields up to 10% F1-score gains over uni-modal training. In out-of-distribution scenarios, even weaker source modalities (e.g., IMU to video) improve target performance, as long as the target model isn't overfitted on the training data. By enabling single-sensor inference with cross-modal knowledge, D-CAT reduces hardware redundancy for perception systems while maintaining accuracy, which is critical for cost-sensitive or adaptive deployments (e.g., assistive robots in homes with variable sensor availability). Code is available at https://github.com/Schindler-EPFL-Lab/D-CAT.

Chenghao Xu, Malcolm Mielle, Antoine Laborde et al.

Achieving the EU's climate neutrality goal requires retrofitting existing buildings to reduce energy use and emissions. A critical step in this process is the precise assessment of geometric building envelope characteristics to inform retrofitting decisions. Previous methods for estimating building characteristics, such as window-to-wall ratio, building footprint area, and the location of architectural elements, have primarily relied on applying deep-learning-based detection or segmentation techniques on 2D images. However, these approaches tend to focus on planar facade properties, limiting their accuracy and comprehensiveness when analyzing complete building envelopes in 3D. While neural scene representations have shown exceptional performance in indoor scene reconstruction, they remain under-explored for external building envelope analysis. This work addresses this gap by leveraging cutting-edge neural surface reconstruction techniques based on signed distance function (SDF) representations for 3D building analysis. We propose BuildNet3D, a novel framework to estimate geometric building characteristics from 2D image inputs. By integrating SDF-based representation with semantic modality, BuildNet3D recovers fine-grained 3D geometry and semantics of building envelopes, which are then used to automatically extract building characteristics. Our framework is evaluated on a range of complex building structures, demonstrating high accuracy and generalizability in estimating window-to-wall ratio and building footprint. The results underscore the effectiveness of BuildNet3D for practical applications in building analysis and retrofitting.

Farida Al Haddad, Yuxin Wang, Malcolm Mielle

Artificial intelligence has the potential to impact safety and efficiency in safety-critical domains such as construction, manufacturing, and healthcare. For example, using sensor data from wearable devices, such as inertial measurement units (IMUs), human gestures can be detected while maintaining privacy, thereby ensuring that safety protocols are followed. However, strict safety requirements in these domains have limited the adoption of AI, since accurate calibration of predicted probabilities and robustness against out-of-distribution (OOD) data is necessary. This paper proposes UAC (Uncertainty-Aware Calibration), a novel two-step method to address these challenges in IMU-based gesture recognition. First, we present an uncertainty-aware gesture network architecture that predicts both gesture probabilities and their associated uncertainties from IMU data. This uncertainty is then used to calibrate the probabilities of each potential gesture. Second, an entropy-weighted expectation of predictions over multiple IMU data windows is used to improve accuracy while maintaining correct calibration. Our method is evaluated using three publicly available IMU datasets for gesture detection and is compared to three state-of-the-art calibration methods for neural networks: temperature scaling, entropy maximization, and Laplace approximation. UAC outperforms existing methods, achieving improved accuracy and calibration in both OOD and in-distribution scenarios. Moreover, we find that, unlike our method, none of the state-of-the-art methods significantly improve the calibration of IMU-based gesture recognition models. In conclusion, our work highlights the advantages of uncertainty-aware calibration of neural networks, demonstrating improvements in both calibration and accuracy for gesture detection using IMU data.

Mariam Hassan, Florent Forest, Olga Fink et al.

Thermal scene reconstruction holds great potential for various applications, such as analyzing building energy consumption and performing non-destructive infrastructure testing. However, existing methods typically require dense scene measurements and often rely on RGB images for 3D geometry reconstruction, projecting thermal information post-reconstruction. This can lead to inconsistencies between the reconstructed geometry and temperature data and their actual values. To address this challenge, we propose ThermoNeRF, a novel multimodal approach based on Neural Radiance Fields that jointly renders new RGB and thermal views of a scene, and ThermoScenes, a dataset of paired RGB+thermal images comprising 8 scenes of building facades and 8 scenes of everyday objects. To address the lack of texture in thermal images, ThermoNeRF uses paired RGB and thermal images to learn scene density, while separate networks estimate color and temperature data. Unlike comparable studies, our focus is on temperature reconstruction and experimental results demonstrate that ThermoNeRF achieves an average mean absolute error of 1.13C and 0.41C for temperature estimation in buildings and other scenes, respectively, representing an improvement of over 50% compared to using concatenated RGB+thermal data as input to a standard NeRF. Code and dataset are available online.

Ali Waseem, Malcolm Mielle

Inverse heat problems refer to the estimation of material thermophysical properties given observed or known heat diffusion behaviour. Inverse heat problems have wide-ranging uses, but a critical application lies in quantifying how building facade renovation reduces thermal transmittance, a key determinant of building energy efficiency. However, solving inverse heat problems with non-invasive data collected in situ is error-prone due to environmental variability or deviations from theoretically assumed conditions. Hence, current methods for measuring thermal conductivity are either invasive, require lengthy observation periods, or are sensitive to environmental and experimental conditions. Here, we present a PINN-based iterative framework to estimate the thermal conductivity k of a wall from a set of thermographs; our framework alternates between estimating the forward heat problem with a PINN for a fixed k, and optimizing k by comparing the thermographs and surface temperatures predicted by the PINN, repeating until the estimated k's convergence. Using both environmental data captured by a weather station and data generated from Finite-Volume-Method software simulations, we accurately predict k across different environmental conditions and data collection sampling times, given the temperature profile of the wall at dawn is close to steady state. Although violating the steady-state assumption impacts the accuracy of k's estimation, we show that our proposed framework still only exhibits a maximum MAE of 4.0851. Our work demonstrates the potential of PINN-based methods for reliable estimation of material properties in situ and under realistic conditions, without lengthy measurement campaigns. Given the lack of research on using machine learning, and more specifically on PINNs, for solving in-situ inverse problems, we expect our work to be a starting point for more research on the topic.

Shuo Sun, Torsten Sattler, Malcolm Mielle et al.

Accurate and robust 3D scene reconstruction from casual, in-the-wild videos can significantly simplify robot deployment to new environments. However, reliable camera pose estimation and scene reconstruction from such unconstrained videos remains an open challenge. Existing visual-only SLAM methods perform well on benchmark datasets but struggle with real-world footage which often exhibits uncontrolled motion including rapid rotations and pure forward movements, textureless regions, and dynamic objects. We analyze the limitations of current methods and introduce a robust pipeline designed to improve 3D reconstruction from casual videos. We build upon recent deep visual odometry methods but increase robustness in several ways. Camera intrinsics are automatically recovered from the first few frames using structure-from-motion. Dynamic objects and less-constrained areas are masked with a predictive model. Additionally, we leverage monocular depth estimates to regularize bundle adjustment, mitigating errors in low-parallax situations. Finally, we integrate place recognition and loop closure to reduce long-term drift and refine both intrinsics and pose estimates through global bundle adjustment. We demonstrate large-scale contiguous 3D models from several online videos in various environments. In contrast, baseline methods typically produce locally inconsistent results at several points, producing separate segments or distorted maps. In lieu of ground-truth pose data, we evaluate map consistency, execution time and visual accuracy of re-rendered NeRF models. Our proposed system establishes a new baseline for visual reconstruction from casual uncontrolled videos found online, demonstrating more consistent reconstructions over longer sequences of in-the-wild videos than previously achieved.

Etienne Chassaing, Florent Forest, Olga Fink et al.

In the European Union, buildings account for 42% of energy use and 35% of greenhouse gas emissions. Since most existing buildings will still be in use by 2050, retrofitting is crucial for emissions reduction. However, current building assessment methods rely mainly on qualitative thermal imaging, which limits data-driven decisions for energy savings. On the other hand, quantitative assessments using finite element analysis (FEA) offer precise insights but require manual CAD design, which is tedious and error-prone. Recent advances in 3D reconstruction, such as Neural Radiance Fields (NeRF) and Gaussian Splatting, enable precise 3D modeling from sparse images but lack clearly defined volumes and the interfaces between them needed for FEA. We propose Thermoxels, a novel voxel-based method able to generate FEA-compatible models, including both geometry and temperature, from a sparse set of RGB and thermal images. Using pairs of RGB and thermal images as input, Thermoxels represents a scene's geometry as a set of voxels comprising color and temperature information. After optimization, a simple process is used to transform Thermoxels' models into tetrahedral meshes compatible with FEA. We demonstrate Thermoxels' capability to generate RGB+Thermal meshes of 3D scenes, surpassing other state-of-the-art methods. To showcase the practical applications of Thermoxels' models, we conduct a simple heat conduction simulation using FEA, achieving convergence from an initial state defined by Thermoxels' thermal reconstruction. Additionally, we compare Thermoxels' image synthesis abilities with current state-of-the-art methods, showing competitive results, and discuss the limitations of existing metrics in assessing mesh quality.

Shuo Sun, Malcolm Mielle, Achim J. Lilienthal et al.

We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM.

Malcolm Mielle, Martin Magnusson, Achim J. Lilienthal

How to divide floor plans or navigation maps into semantic representations, such as rooms and corridors, is an important research question in fields such as human-robot interaction, place categorization, or semantic mapping. While most works focus on segmenting robot built maps, those are not the only types of map a robot, or its user, can use. We present a method for segmenting maps from different modalities, focusing on robot built maps and hand-drawn sketch maps, and show better results than state of the art for both types. Our method segments the map by doing a convolution between the distance image of the map and a circular kernel, and grouping pixels of the same value. Segmentation is done by detecting ripple-like patterns where pixel values varies quickly, and merging neighboring regions with similar values. We identify a flaw in the segmentation evaluation metric used in recent works and propose a metric based on Matthews correlation coefficient (MCC). We compare our results to ground-truth segmentations of maps from a publicly available dataset, on which we obtain a better MCC than the state of the art with 0.98 compared to 0.65 for a recent Voronoi-based segmentation method and 0.70 for the DuDe segmentation method. We also provide a dataset of sketches of an indoor environment, with two possible sets of ground truth segmentations, on which our method obtains an MCC of 0.56 against 0.28 for the Voronoi-based segmentation method and 0.30 for DuDe.

Malcolm Mielle, Martin Magnusson, Henrik Andreasson et al.

In search and rescue missions, time is an important factor; fast navigation and quickly acquiring situation awareness might be matters of life and death. Hence, the use of robots in such scenarios has been restricted by the time needed to explore and build a map. One way to speed up exploration and mapping is to reason about unknown parts of the environment using prior information. While previous research on using external priors for robot mapping mainly focused on accurate maps or aerial images, such data are not always possible to get, especially indoor. We focus on emergency maps as priors for robot mapping since they are easy to get and already extensively used by firemen in rescue missions. However, those maps can be outdated, information might be missing, and the scales of rooms are typically not consistent. We have developed a formulation of graph-based SLAM that incorporates information from an emergency map. The graph-SLAM is optimized using a combination of robust kernels, fusing the emergency map and the robot map into one map, even when faced with scale inaccuracies and inexact start poses. We typically have more than 50% of wrong correspondences in the settings studied in this paper, and the method we propose correctly handles them. Experiments in an office environment show that we can handle up to 70% of wrong correspondences and still get the expected result. The robot can navigate and explore while taking into account places it has not yet seen. We demonstrate this in a test scenario and also show that the emergency map is enhanced by adding information not represented such as closed doors or new walls.