arXiv subjects

Didier Stricker

Publications and source records attributed to Didier Stricker.

At least 55 records · Page 3Linked to original sources

arXiv2025

Beyond Averages: Open-Vocabulary 3D Scene Understanding with Gaussian Splatting and Bag of Embeddings

Novel view synthesis has seen significant advancements with 3D Gaussian Splatting (3DGS), enabling real-time photorealistic rendering. However, the inherent fuzziness of Gaussian Splatting presents challenges for 3D scene understanding, restricting its broader applications in AR/VR and robotics. While recent works attempt to learn semantics via 2D foundation model distillation, they inherit fundamental limitations: alpha blending averages semantics across objects, making 3D-level understanding impossible. We propose a paradigm-shifting alternative that bypasses differentiable rendering for semantics entirely. Our key insight is to leverage predecomposed object-level Gaussians and represent each object through multiview CLIP feature aggregation, creating comprehensive "bags of embeddings" that holistically describe objects. This allows: (1) accurate open-vocabulary object retrieval by comparing text queries to object-level (not Gaussian-level) embeddings, and (2) seamless task adaptation: propagating object IDs to pixels for 2D segmentation or to Gaussians for 3D extraction. Experiments demonstrate that our method effectively overcomes the challenges of 3D open-vocabulary object extraction while remaining comparable to state-of-the-art performance in 2D open-vocabulary segmentation, ensuring minimal compromise.

cs.CV↗

arXiv2025

MinJointTracker: Real-time inertial kinematic chain tracking with joint position estimation and minimal state size

Inertial motion capture is a promising approach for capturing motion outside the laboratory. However, as one major drawback, most of the current methods require different quantities to be calibrated or computed offline as part of the setup process, such as segment lengths, relative orientations between inertial measurement units (IMUs) and segment coordinate frames (IMU-to-segment calibrations) or the joint positions in the IMU frames. This renders the setup process inconvenient. This work contributes to real-time capable calibration-free inertial tracking of a kinematic chain, i.e. simultaneous recursive Bayesian estimation of global IMU angular kinematics and joint positions in the IMU frames, with a minimal state size. Experimental results on simulated IMU data from a three-link kinematic chain (manipulator study) as well as re-simulated IMU data from healthy humans walking (lower body study) show that the calibration-free and lightweight algorithm provides not only drift-free relative but also drift-free absolute orientation estimates with a global heading reference for only one IMU as well as robust and fast convergence of joint position estimates in the different movement scenarios.

cs.RO↗

arXiv2025

ParticleSAM: Small Particle Segmentation for Material Quality Monitoring in Recycling Processes

The construction industry represents a major sector in terms of resource consumption. Recycled construction material has high reuse potential, but quality monitoring of the aggregates is typically still performed with manual methods. Vision-based machine learning methods could offer a faster and more efficient solution to this problem, but existing segmentation methods are by design not directly applicable to images with hundreds of small particles. In this paper, we propose ParticleSAM, an adaptation of the segmentation foundation model to images with small and dense objects such as the ones often encountered in construction material particles. Moreover, we create a new dense multi-particle dataset simulated from isolated particle images with the assistance of an automated data generation and labeling pipeline. This dataset serves as a benchmark for visual material quality control automation while our segmentation approach has the potential to be valuable in application areas beyond construction where small-particle segmentation is needed. Our experimental results validate the advantages of our method by comparing to the original SAM method both in quantitative and qualitative experiments.

cs.CV↗

arXiv2025

Breaking the mould of Social Mixed Reality - State-of-the-Art and Glossary

This article explores a critical gap in Mixed Reality (MR) technology: while advances have been made, MR still struggles to authentically replicate human embodiment and socio-motor interaction. For MR to enable truly meaningful social experiences, it needs to incorporate multi-modal data streams and multi-agent interaction capabilities. To address this challenge, we present a comprehensive glossary covering key topics such as Virtual Characters and Autonomisation, Responsible AI, Ethics by Design, and the Scientific Challenges of Social MR within Neuroscience, Embodiment, and Technology. Our aim is to drive the transformative evolution of MR technologies that prioritize human-centric innovation, fostering richer digital connections. We advocate for MR systems that enhance social interaction and collaboration between humans and virtual autonomous agents, ensuring inclusivity, ethical design and psychological safety in the process.

cs.HC↗

arXiv2025

CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation

In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of limited data access, without any restrictions imposed on computational resources. However, in real-world scenarios, the latter takes precedence as deployed systems are often computationally constrained. A major drawback of most CL methods is the need to retrain the entire model for each new task. The computational demands of retraining large models can be prohibitive, limiting the applicability of CL in environments with limited resources. Through CLoRA, we explore the applicability of Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method for class-incremental semantic segmentation. CLoRA leverages a small set of parameters of the model and uses the same set for learning across all tasks. Results demonstrate the efficacy of CLoRA, achieving performance on par with and exceeding the baseline methods. We further evaluate CLoRA using NetScore, underscoring the need to factor in resource efficiency and evaluate CL methods beyond task performance. CLoRA significantly reduces the hardware requirements for training, making it well-suited for CL in resource-constrained environments after deployment.

cs.LG↗

arXiv2025

JENGA: Object selection and pose estimation for robotic grasping from a stack

Vision-based robotic object grasping is typically investigated in the context of isolated objects or unstructured object sets in bin picking scenarios. However, there are several settings, such as construction or warehouse automation, where a robot needs to interact with a structured object formation such as a stack. In this context, we define the problem of selecting suitable objects for grasping along with estimating an accurate 6DoF pose of these objects. To address this problem, we propose a camera-IMU based approach that prioritizes unobstructed objects on the higher layers of stacks and introduce a dataset for benchmarking and evaluation, along with a suitable evaluation metric that combines object selection with pose accuracy. Experimental results show that although our method can perform quite well, this is a challenging problem if a completely error-free solution is needed. Finally, we show results from the deployment of our method for a brick-picking application in a construction scenario.

cs.RO↗

arXiv2025

Towards Unconstrained 2D Pose Estimation of the Human Spine

We present SpineTrack, the first comprehensive dataset for 2D spine pose estimation in unconstrained settings, addressing a crucial need in sports analytics, healthcare, and realistic animation. Existing pose datasets often simplify the spine to a single rigid segment, overlooking the nuanced articulation required for accurate motion analysis. In contrast, SpineTrack annotates nine detailed spinal keypoints across two complementary subsets: a synthetic set comprising 25k annotations created using Unreal Engine with biomechanical alignment through OpenSim, and a real-world set comprising over 33k annotations curated via an active learning pipeline that iteratively refines automated annotations with human feedback. This integrated approach ensures anatomically consistent labels at scale, even for challenging, in-the-wild images. We further introduce SpinePose, extending state-of-the-art body pose estimators using knowledge distillation and an anatomical regularization strategy to jointly predict body and spine keypoints. Our experiments in both general and sports-specific contexts validate the effectiveness of SpineTrack for precise spine pose estimation, establishing a robust foundation for future research in advanced biomechanical analysis and 3D spine reconstruction in the wild.

cs.CV↗

arXiv2025

3D Spatial Understanding in MLLMs: Disambiguation and Evaluation

Multimodal Large Language Models (MLLMs) have made significant progress in tasks such as image captioning and question answering. However, while these models can generate realistic captions, they often struggle with providing precise instructions, particularly when it comes to localizing and disambiguating objects in complex 3D environments. This capability is critical as MLLMs become more integrated with collaborative robotic systems. In scenarios where a target object is surrounded by similar objects (distractors), robots must deliver clear, spatially-aware instructions to guide humans effectively. We refer to this challenge as contextual object localization and disambiguation, which imposes stricter constraints than conventional 3D dense captioning, especially regarding ensuring target exclusivity. In response, we propose simple yet effective techniques to enhance the model's ability to localize and disambiguate target objects. Our approach not only achieves state-of-the-art performance on conventional metrics that evaluate sentence similarity, but also demonstrates improved 3D spatial understanding through 3D visual grounding model.

cs.CV↗

arXiv2025

Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models

Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96% smaller and up to 71% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.

cs.CV↗

arXiv2025

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

Generating high-fidelity 3D content from text prompts remains a significant challenge in computer vision due to the limited size, diversity, and annotation depth of the existing datasets. To address this, we introduce MARVEL-40M+, an extensive dataset with 40 million text annotations for over 8.9 million 3D assets aggregated from seven major 3D datasets. Our contribution is a novel multi-stage annotation pipeline that integrates open-source pretrained multi-view VLMs and LLMs to automatically produce multi-level descriptions, ranging from detailed (150-200 words) to concise semantic tags (10-20 words). This structure supports both fine-grained 3D reconstruction and rapid prototyping. Furthermore, we incorporate human metadata from source datasets into our annotation pipeline to add domain-specific information in our annotation and reduce VLM hallucinations. Additionally, we develop MARVEL-FX3D, a two-stage text-to-3D pipeline. We fine-tune Stable Diffusion with our annotations and use a pretrained image-to-3D network to generate 3D textured meshes within 15s. Extensive evaluations show that MARVEL-40M+ significantly outperforms existing datasets in annotation quality and linguistic diversity, achieving win rates of 72.41% by GPT-4 and 73.40% by human evaluators. Project page is available at https://sankalpsinha-cmos.github.io/MARVEL/.

cs.CV↗

arXiv2025

Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies

We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple mentors with different knowledge levels. Unlike traditional methods that rely on fixed mentor-student relationships, our framework dynamically selects and adapts the teaching strategies of diverse mentors based on their effectiveness for each data sample. ClassroomKD comprises two main modules: the Knowledge Filtering (KF) module and the Mentoring module. The KF Module dynamically ranks mentors based on their performance for each input, activating only high-quality mentors to minimize error accumulation and prevent information loss. The Mentoring Module adjusts the distillation strategy by tuning each mentor's influence according to the dynamic performance gap between the student and mentors, effectively modulating the learning pace. Extensive experiments on image classification (CIFAR-100 and ImageNet) and 2D human pose estimation (COCO Keypoints and MPII Human Pose) demonstrate that ClassroomKD outperforms existing knowledge distillation methods for different network architectures. Our results highlight that a dynamic and adaptive approach to mentor selection and guidance leads to more effective knowledge transfer, paving the way for enhanced model performance through distillation.

cs.CV↗

arXiv2025

EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera

Monocular egocentric 3D human motion capture remains a significant challenge, particularly under conditions of low lighting and fast movements, which are common in head-mounted device applications. Existing methods that rely on RGB cameras often fail under these conditions. To address these limitations, we introduce EventEgo3D++, the first approach that leverages a monocular event camera with a fisheye lens for 3D human motion capture. Event cameras excel in high-speed scenarios and varying illumination due to their high temporal resolution, providing reliable cues for accurate 3D human motion capture. EventEgo3D++ leverages the LNES representation of event streams to enable precise 3D reconstructions. We have also developed a mobile head-mounted device (HMD) prototype equipped with an event camera, capturing a comprehensive dataset that includes real event observations from both controlled studio environments and in-the-wild settings, in addition to a synthetic dataset. Additionally, to provide a more holistic dataset, we include allocentric RGB streams that offer different perspectives of the HMD wearer, along with their corresponding SMPL body model. Our experiments demonstrate that EventEgo3D++ achieves superior 3D accuracy and robustness compared to existing solutions, even in challenging conditions. Moreover, our method supports real-time 3D pose updates at a rate of 140Hz. This work is an extension of the EventEgo3D approach (CVPR 2024) and further advances the state of the art in egocentric 3D human motion capture. For more details, visit the project page at https://eventego3d.mpi-inf.mpg.de.

cs.CV↗

arXiv2025

SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance

Large language models (LLMs) have achieved remarkable success in text-based tasks but often struggle to provide actionable guidance in real-world physical environments. This is because of their inability to recognize their limited understanding of the user's physical context. We present SituationalLLM, a novel approach that integrates structured scene information into an LLM to deliver proactive, context-aware assistance. By encoding objects, attributes, and relationships in a custom Scene Graph Language, SituationalLLM actively identifies gaps in environmental context and seeks clarifications during user interactions. This behavior emerges from training on the Situational Awareness Database for Instruct-Tuning (SAD-Instruct), which combines diverse, scenario-specific scene graphs with iterative, dialogue-based refinements. Experimental results indicate that SituationalLLM outperforms generic LLM baselines in task specificity, reliability, and adaptability, paving the way for environment-aware AI assistants capable of delivering robust, user-centric guidance under real-world constraints.

cs.CV↗

arXiv2025

Domain-Incremental Semantic Segmentation for Autonomous Driving under Adverse Driving Conditions

Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weather or illumination conditions. Fine-tuning on the new task or condition would lead to overwriting the previously learned information resulting in catastrophic forgetting. Adapting to the new conditions through traditional domain adaption methods improves the performance on the target domain at the expense of the source domain. Addressing these issues, we propose an architecture-based domain-incremental learning approach called Progressive Semantic Segmentation (PSS). PSS is a task-agnostic, dynamically growing collection of domain-specific segmentation models. The task of inferring the domain and subsequently selecting the appropriate module for segmentation is carried out using a collection of convolutional autoencoders. We extensively evaluate our proposed approach using several datasets at varying levels of granularity in the categorization of adverse driving conditions. Furthermore, we demonstrate the generalization of the proposed approach to similar and unseen domains.

cs.CV↗

arXiv2024

Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection

The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to the inclusion of background information. We introduce a novel instance mask-based feature aggregation approach, significantly refining this process and deepening the understanding of object dynamics across video frames. We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features. In particular, we propose the lightweight Instance Feature Extraction Module (IFEM) to learn instance mask features and the Temporal Instance Classification Aggregation Module (TICAM) to aggregate instance mask and classification features across video frames. Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU, setting a new benchmark for the speed-accuracy trade-off. Additional experiments on multiple datasets validate that our approach is robust, method-agnostic, and effective in multi-object tracking, demonstrating its broader applicability to video understanding tasks.

cs.CV↗

arXiv2024

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.

cs.CV↗

arXiv2024

Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction

Neural implicit fields have recently emerged as a powerful representation method for multi-view surface reconstruction due to their simplicity and state-of-the-art performance. However, reconstructing thin structures of indoor scenes while ensuring real-time performance remains a challenge for dense visual SLAM systems. Previous methods do not consider varying quality of input RGB-D data and employ fixed-frequency mapping process to reconstruct the scene, which could result in the loss of valuable information in some frames. In this paper, we propose Uni-SLAM, a decoupled 3D spatial representation based on hash grids for indoor reconstruction. We introduce a novel defined predictive uncertainty to reweight the loss function, along with strategic local-to-global bundle adjustment. Experiments on synthetic and real-world datasets demonstrate that our system achieves state-of-the-art tracking and mapping accuracy while maintaining real-time performance. It significantly improves over current methods with a 25% reduction in depth L1 error and a 66.86% completion rate within 1 cm on the Replica dataset, reflecting a more accurate reconstruction of thin structures. Project page: https://shaoxiang777.github.io/project/uni-slam/

cs.CV↗

arXiv2024

Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation

In autonomous driving, environment perception has significantly advanced with the utilization of deep learning techniques for diverse sensors such as cameras, depth sensors, or infrared sensors. The diversity in the sensor stack increases the safety and contributes to robustness against adverse weather and lighting conditions. However, the variance in data acquired from different sensors poses challenges. In the context of continual learning (CL), incremental learning is especially challenging for considerably large domain shifts, e.g. different sensor modalities. This amplifies the problem of catastrophic forgetting. To address this issue, we formulate the concept of modality-incremental learning and examine its necessity, by contrasting it with existing incremental learning paradigms. We propose the use of a modified Relevance Mapping Network (RMN) to incrementally learn new modalities while preserving performance on previously learned modalities, in which relevance maps are disjoint. Experimental results demonstrate that the prevention of shared connections in this approach helps alleviate the problem of forgetting within the constraints of a strict continual learning framework.

cs.CV↗