arXiv subjects

Simon Schaefer

Publications and source records attributed to Simon Schaefer.

At least 19 recordsLinked to original sources

arXiv2026

Scalix: Uncertainty-Aware Scale-Consistent Monocular SLAM

Cameras are ubiquitous sensors in robotics due to their compact form factor and the perceptual richness captured through visual information. Monocular SLAM enables robots to understand the environment with a minimum setup, however, it inherently suffers from scale ambiguity. A common solution is to provide multi-modal sensor configurations, such as visual-inertial systems, where scale is observable unless the robot navigates under a constant-velocity motion, a common scenario in mobile robotics. With the advent of deep-learning, geometric foundation models have been used to address this problem, but the depths maps are often noisy and scale-inconsistent across frames. In this paper, we propose Scalix, a real-time monocular SLAM framework that achieves metric-scale state estimation by integrating learned depth cues into a probabilistic factor-graph formulation. By augmenting existing monocular depth models with both per-pixel depth uncertainty and per-frame scale uncertainty, Scalix treats scale predictions as independent measurements within its optimization, leading to improved scale consistency through multi-view data associations. Experiments in large-scale outdoor and indoor environments demonstrate state-of-the-art performance on both metric and up-to-scale benchmarks while maintaining real-time operation and generalization.

cs.RO↗

arXiv2026

SpotlessGS: Relightable 3D Gaussian Splatting under Dynamic Illumination for Robotic Perception

Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perception tasks. Prior approaches based on 2D image enhancement lack reliable supervision and fail to preserve multi-view geometric consistency. To address these limitations, we extend Dark Gaussian Splatting (DarkGS) toward a more accurate and flexible relightable 3D reconstruction framework. First, we eliminate the need for explicit light parameter calibration by jointly optimizing lighting parameters within the Gaussian Splatting framework. Second, we introduce a low-frequency illumination model based on spherical harmonics (SH) to capture spatially varying residual and ambient lighting effects. Third, we incorporate an MLP-based Bidirectional Reflectance Distribution Function (BRDF) to model non-Lambertian reflectance. Experiments on synthetic and real-world datasets demonstrate that our method effectively mitigates illumination artifacts while improving rendering quality and quantitative performance over prior approaches. We further validate its benefits for robotic perception through a downstream task.

cs.RO↗

arXiv2026

Robot Self-Improvement via Human-Video Dynamics Models

A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, and the experience of failure. Human videos provide the first of these in abundance, and prior work has shown they can initialize useful policies. Far less clear is whether they can support the second and third: whether priors extracted from human videos can ground a robot's own attempts well enough to evaluate them, correct them, and improve from them. In this work, we show that human videos can be used to learn embodiment-agnostic action, dynamics, and value representations that transfer across robot embodiments, providing the predictive foundation required for robots to autonomously improve from their own rollouts and failures. We introduce Dynamics-Guided Action Correction (DGAC), a training-free approach that leverages these adapted models to repair failed states: each failure becomes a query for which the learned models propose and rank corrective actions, turning failures into supervision for the next policy update. Across seven real-world manipulation tasks spanning both a mobile manipulator and a static manipulator arm, our approach improves success rates from 40% to 81% across multiple policy backbones, demonstrating cross-embodiment robot self-improvement from human-video priors. These results show that human priors and robot failures can be combined to enable scalable autonomous policy improvement. Project page: https://ethz-mrl.github.io/robot-self-improvement-website/.

cs.RO↗

arXiv2026

HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control

Robust and accurate perception of humans in their 3D scene context is essential for integrating robots into everyday environments. Existing approaches, however, often fail to predict plausible and accurate human motion estimates that are consistent with the surrounding scene, especially in the presence of heavy occlusions or partial visibility. This can limit both safety and efficiency for robotic operations. We introduce HumanFlow, a latent diffusion model that unifies human motion tracking and forecasting, conditioned on the 3D scene context. We show that our human motion model produces smooth and accurate predictions under challenging conditions, including heavy occlusions, and outperforms state-of-the-art methods in tracking accuracy while being significantly more efficient. Furthermore, we show how HumanFlow's latent space can be tightly coupled with control by conditioning a flow-matching-based, approximate MPC policy on these representations. We validate our policy in simulation with real human trajectories for MAV social navigation, demonstrating superior navigation performance and remaining collision-free, even under partial observability of the human.

cs.RO↗

arXiv2026

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.

cs.CV↗

arXiv2025

HumanHalo -- Safe and Efficient 3D Navigation Among Humans via Minimally Conservative MPC

Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on simplified 2D crowd navigation and fail to account for the full complexity of human body dynamics beyond root motion. We present HumanHalo, a Model Predictive Control (MPC) framework for 3D Micro Air Vehicle (MAV) navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel twist to reachability-based safety formulation that constrains only the initial control input for safety while modeling its effects over the entire planning horizon, enabling safe yet efficient navigation. We validate HumanHalo in both simulated experiments using real human trajectories and in the real-world, demonstrating its effectiveness across tasks ranging from goal-directed navigation to visual servoing for human tracking. While we apply our method to MAVs in this work, it is generic and can be adapted by other platforms. Our results show that the method ensures safety without excessive conservatism and outperforms baseline approaches in both efficiency and reliability.

cs.RO↗

arXiv2025

GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement

Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires reasoning about both semantic preferences (e.g., common-sense object relations) and geometric feasibility (e.g., collision avoidance). We present GOPLA, a hierarchical framework that learns generalizable object placement from augmented human demonstrations. A multi-modal large language model translates human instructions and visual inputs into structured plans that specify pairwise object relationships. These plans are then converted into 3D affordance maps with geometric common sense by a spatial mapper, while a diffusion-based planner generates placement poses guided by test-time costs, considering multi-plan distributions and collision avoidance. To overcome data scarcity, we introduce a scalable pipeline that expands human placement demonstrations into diverse synthetic training data. Extensive experiments show that our approach improves placement success rates by 30.04 percentage points over the runner-up, evaluated on positioning accuracy and physical plausibility, demonstrating strong generalization across a wide range of real-world robotic placement scenarios.

cs.RO↗

arXiv2025

GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting

Recent developments in 3D Gaussian Splatting have significantly enhanced novel view synthesis, yet generating high-quality renderings from extreme novel viewpoints or partially observed regions remains challenging. Meanwhile, diffusion models exhibit strong generative capabilities, but their reliance on text prompts and lack of awareness of specific scene information hinder accurate 3D reconstruction tasks. To address these limitations, we introduce GSFix3D, a novel framework that improves the visual fidelity in under-constrained regions by distilling prior knowledge from diffusion models into 3D representations, while preserving consistency with observed scene details. At its core is GSFixer, a latent diffusion model obtained via our customized fine-tuning protocol that can leverage both mesh and 3D Gaussians to adapt pretrained generative models to a variety of environments and artifact types from different reconstruction methods, enabling robust novel view repair for unseen camera poses. Moreover, we propose a random mask augmentation strategy that empowers GSFixer to plausibly inpaint missing regions. Experiments on challenging benchmarks demonstrate that our GSFix3D and GSFixer achieve state-of-the-art performance, requiring only minimal scene-specific fine-tuning on captured data. Real-world test further confirms its resilience to potential pose errors. Our code and data will be made publicly available. Project page: https://gsfix3d.github.io.

cs.CV↗

arXiv2025

FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment

Geometrically accurate and semantically expressive map representations have proven invaluable for robot deployment and task planning in unknown environments. Nevertheless, real-time, open-vocabulary semantic understanding of large-scale unknown environments still presents open challenges, mainly due to computational requirements. In this paper we present FindAnything, an open-world mapping framework that incorporates vision-language information into dense volumetric submaps. Thanks to the use of vision-language features, FindAnything combines pure geometric and open-vocabulary semantic information for a higher level of understanding. It proposes an efficient storage of open-vocabulary information through the aggregation of features at the object level. Pixelwise vision-language features are aggregated based on eSAM segments, which are in turn integrated into object-centric volumetric submaps, providing a mapping from open-vocabulary queries to 3D geometry that is scalable also in terms of memory usage. We demonstrate that FindAnything performs on par with the state-of-the-art in terms of semantic accuracy while being substantially faster and more memory-efficient, allowing its deployment in large-scale environments and on resourceconstrained devices, such as MAVs. We show that the real-time capabilities of FindAnything make it useful for downstream tasks, such as autonomous MAV exploration in a simulated Search and Rescue scenario. Project Page: https://ethz-mrl.github.io/findanything/.

cs.RO↗

arXiv2025

SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM

Event-based keypoint detection and matching holds significant potential, enabling the integration of event sensors into highly optimized Visual SLAM systems developed for frame cameras over decades of research. Unfortunately, existing approaches struggle with the motion-dependent appearance of keypoints and the complex noise prevalent in event streams, resulting in severely limited feature matching capabilities and poor performance on downstream tasks. To mitigate this problem, we propose SuperEvent, a data-driven approach to predict stable keypoints with expressive descriptors. Due to the absence of event datasets with ground truth keypoint labels, we leverage existing frame-based keypoint detectors on readily available event-aligned and synchronized gray-scale frames for self-supervision: we generate temporally sparse keypoint pseudo-labels considering that events are a product of both scene appearance and camera motion. Combined with our novel, information-rich event representation, we enable SuperEvent to effectively learn robust keypoint detection and description in event streams. Finally, we demonstrate the usefulness of SuperEvent by its integration into a modern sparse keypoint and descriptor-based SLAM framework originally developed for traditional cameras, surpassing the state-of-the-art in event-based SLAM by a wide margin. Source code is available at https://ethz-mrl.github.io/SuperEvent/.

cs.CV↗

arXiv2024

Online Tree Reconstruction and Forest Inventory on a Mobile Robotic System

Terrestrial laser scanning (TLS) is the standard technique used to create accurate point clouds for digital forest inventories. However, the measurement process is demanding, requiring up to two days per hectare for data collection, significant data storage, as well as resource-heavy post-processing of 3D data. In this work, we present a real-time mapping and analysis system that enables online generation of forest inventories using mobile laser scanners that can be mounted e.g. on mobile robots. Given incrementally created and locally accurate submaps-data payloads-our approach extracts tree candidates using a custom, Voronoi-inspired clustering algorithm. Tree candidates are reconstructed using an adapted Hough algorithm, which enables robust modeling of the tree stem. Further, we explicitly incorporate the incremental nature of the data collection by consistently updating the database using a pose graph LiDAR SLAM system. This enables us to refine our estimates of the tree traits if an area is revisited later during a mission. We demonstrate competitive accuracy to TLS or manual measurements using laser scanners that we mounted on backpacks or mobile robots operating in conifer, broad-leaf and mixed forests. Our results achieve RMSE of 1.93 cm, a bias of 0.65 cm and a standard deviation of 1.81 cm (averaged across these sequences)-with no post-processing required after the mission is complete.

cs.RO↗

arXiv2024

SC-Diff: 3D Shape Completion with Latent Diffusion Models

We present a novel 3D shape completion framework that unifies multimodal conditioning, leveraging both 2D images and 3D partial scans through a latent diffusion model. Shapes are represented as Truncated Signed Distance Functions (TSDFs) and encoded into a discrete latent space jointly supervised by 2D and 3D cues, enabling efficient high-resolution processing while reducing GPU memory usage by 30\% compared to state-of-the-art methods. Our approach guides the generation process with flexible multimodal conditioning, ensuring consistent integration of 2D and 3D information from encoding to reconstruction. Our training strategy simulates realistic partial observations, avoiding assumptions about input structure and improving robustness in real-world scenarios. Leveraging our efficient latent space and multimodal conditioning, our model generalizes across object categories, outperforming class-specific models by 12\% and class-agnostic models by 47\% in $l_1$ reconstruction error, while producing more diverse, realistic, and high-fidelity completions than prior approaches.

cs.CV↗

arXiv2024

DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks

The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images within the static part of the environment, we propose a graph neural network-based sparse feature matching network designed to perform robust matching under challenging conditions while excluding keypoints on moving objects. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks but augment the graph with epipolar and temporal information and vastly reduce the number of graph edges. Furthermore, we introduce a self-supervised training scheme to extract pseudo labels for image pairs in dynamic environments from exclusively unprocessed visual-inertial data. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks while still achieving similar results regarding conventional matching metrics. When integrated into a SLAM system, our network significantly improves performance, especially in highly dynamic scenes.

cs.CV↗

arXiv2024

Scalable Outdoors Autonomous Drone Flight with Visual-Inertial SLAM and Dense Submaps Built without LiDAR

Autonomous navigation is needed for several robotics applications. In this paper we present an autonomous Micro Aerial Vehicle (MAV) system which purely relies on cost-effective and light-weight passive visual and inertial sensors to perform large-scale autonomous navigation in outdoor,unstructured and cluttered environments. We leverage visual-inertial simultaneous localization and mapping (VI-SLAM) for accurate MAV state estimates and couple it with a volumetric occupancy submapping system to achieve a scalable mapping framework which can be directly used for path planning. To ensure the safety of the MAV during navigation, we also propose a novel reference trajectory anchoring scheme that deforms the reference trajectory the MAV is tracking upon state updates from the VI-SLAM system in a consistent way, even upon large state updates due to loop-closures. We thoroughly validate our system in both real and simulated forest environments and at peak velocities up to 3 m/s while not encountering a single collision or system failure. To the best of our knowledge, this is the first system which achieves this level of performance in such an unstructured environment using low-cost passive visual sensors and fully on-board computation, including VI-SLAM.

cs.RO↗

arXiv2023

GloPro: Globally-Consistent Uncertainty-Aware 3D Human Pose Estimation & Tracking in the Wild

An accurate and uncertainty-aware 3D human body pose estimation is key to enabling truly safe but efficient human-robot interactions. Current uncertainty-aware methods in 3D human pose estimation are limited to predicting the uncertainty of the body posture, while effectively neglecting the body shape and root pose. In this work, we present GloPro, which to the best of our knowledge the first framework to predict an uncertainty distribution of a 3D body mesh including its shape, pose, and root pose, by efficiently fusing visual clues with a learned motion model. We demonstrate that it vastly outperforms state-of-the-art methods in terms of human trajectory accuracy in a world coordinate system (even in the presence of severe occlusions), yields consistent uncertainty distributions, and can run in real-time.

cs.CV↗

arXiv2023

BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking

Robust, fast, and accurate human state - 6D pose and posture - estimation remains a challenging problem. For real-world applications, the ability to estimate the human state in real-time is highly desirable. In this paper, we present BodySLAM++, a fast, efficient, and accurate human and camera state estimation framework relying on visual-inertial data. BodySLAM++ extends an existing visual-inertial state estimation framework, OKVIS2, to solve the dual task of estimating camera and human states simultaneously. Our system improves the accuracy of both human and camera state estimation with respect to baseline methods by 26% and 12%, respectively, and achieves real-time performance at 15+ frames per second on an Intel i7-model CPU. Experiments were conducted on a custom dataset containing both ground truth human and camera poses collected with an indoor motion tracking system.

cs.CV↗

arXiv2023

Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning

While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma's Revenge - one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to a HRL agent that is significantly more sample efficient than previous methods.

cs.LG↗

arXiv2022

The Software Stack That Won the Formula Student Driverless Competition

This report describes our approach to design and evaluate a software stack for a race car capable of achieving competitive driving performance in the different disciplines of the Formula Student Driverless. By using a 360{\deg} LiDAR and optionally three cameras, we reliably recognize the plastic cones that mark the track boundaries at distances of around 35 m, enabling us to drive at the physical limits of the car. Using a GraphSLAM algorithm, we are able to map these cones with a root-mean-square error of less than 15 cm while driving at speeds of over 70 kph on a narrow track. The high-precision map is used in the trajectory planning to detect the lane boundaries using Delaunay triangulation and a parametric cubic spline. We calculate an optimized trajectory using a minimum curvature approach together with a GGS-diagram that takes the aerodynamics at different velocities into account. To track the target path with accelerations of up to 1.6 g, the control system is split into a PI controller for longitudinal control and model predictive controller for lateral control. Additionally, a low-level optimal control allocation is used. The software is realized in ROS C++ and tested in a custom simulation, as well as on the actual race track.

cs.RO↗