Technical Report for ICRA 2025 GOOSE 3D Semantic Segmentation Challenge: Adaptive Point Cloud Understanding for Heterogeneous Robotic Systems

This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured outdoor environments collected from multiple robotic platforms. This problem was addressed by implementing Point Prompt Tuning (PPT) integrated with Point Transformer v3 (PTv3) backbone, enabling adaptive processing of heterogeneous LiDAR data through platform-specific conditioning and cross-dataset class alignment strategies. The model is trained without requiring additional external data. As a result, this approach achieved substantial performance improvements with mIoU increases of up to 22.59% on challenging platforms compared to the baseline PTv3 model, demonstrating the effectiveness of adaptive point cloud understanding for field robotics applications.

LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds

We study the problem of unsupervised 3D semantic segmentation on raw point clouds without needing human labels in training. Existing methods usually formulate this problem into learning per-point local features followed by a simple grouping strategy, lacking the ability to discover additional and possibly richer semantic priors beyond local features. In this paper, we introduce LogoSP to learn 3D semantics from both local and global point features. The key to our approach is to discover 3D semantic information by grouping superpoints according to their global patterns in the frequency domain, thus generating highly accurate semantic pseudo-labels for training a segmentation network. Extensive experiments on two indoor and an outdoor datasets show that our LogoSP surpasses all existing unsupervised methods by large margins, achieving the state-of-the-art performance for unsupervised 3D semantic segmentation. Notably, our investigation into the learned global patterns reveals that they truly represent meaningful 3D semantics in the absence of human labels during training.

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

Semantic scene completion (SSC) aims to infer both the 3D geometry and semantics of a scene from single images. In contrast to prior work on SSC that heavily relies on expensive ground-truth annotations, we approach SSC in an unsupervised setting. Our novel method, SceneDINO, adapts techniques from self-supervised representation learning and 2D unsupervised scene understanding to SSC. Our training exclusively utilizes multi-view consistency self-supervision without any form of semantic or geometric ground truth. Given a single input image, SceneDINO infers the 3D geometry and expressive 3D DINO features in a feed-forward manner. Through a novel 3D feature distillation approach, we obtain unsupervised 3D semantics. In both 3D and 2D unsupervised scene understanding, SceneDINO reaches state-of-the-art segmentation accuracy. Linear probing our 3D features matches the segmentation accuracy of a current supervised SSC approach. Additionally, we showcase the domain generalization and multi-view consistency of SceneDINO, taking the first steps towards a strong foundation for single image 3D scene understanding.

TSDASeg: A Two-Stage Model with Direct Alignment for Interactive Point Cloud Segmentation

The rapid advancement of 3D vision-language models (VLMs) has spurred significant interest in interactive point cloud processing tasks, particularly for real-world applications. However, existing methods often underperform in point-level tasks, such as segmentation, due to missing direct 3D-text alignment, limiting their ability to link local 3D features with textual context. To solve this problem, we propose TSDASeg, a Two-Stage model coupled with a Direct cross-modal Alignment module and memory module for interactive point cloud Segmentation. We introduce the direct cross-modal alignment module to establish explicit alignment between 3D point clouds and textual/2D image data. Within the memory module, we employ multiple dedicated memory banks to separately store text features, visual features, and their cross-modal correspondence mappings. These memory banks are dynamically leveraged through self-attention and cross-attention mechanisms to update scene-specific features based on prior stored data, effectively addressing inconsistencies in interactive segmentation results across diverse scenarios. Experiments conducted on multiple 3D instruction, reference, and semantic segmentation datasets demonstrate that the proposed method achieves state-of-the-art performance.

A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects

Multi-sensor fusion perception (MSFP) is a key technology for embodied AI, which can serve a variety of downstream tasks (e.g., 3D object detection and semantic segmentation) and application scenarios (e.g., autonomous driving and swarm robotics). Recently, impressive achievements on AI-based MSFP methods have been reviewed in relevant surveys. However, we observe that the existing surveys have some limitations after a rigorous and detailed investigation. For one thing, most surveys are oriented to a single task or research field, such as 3D object detection or autonomous driving. Therefore, researchers in other related tasks often find it difficult to benefit directly. For another, most surveys only introduce MSFP from a single perspective of multi-modal fusion, while lacking consideration of the diversity of MSFP methods, such as multi-view fusion and time-series fusion. To this end, in this paper, we hope to organize MSFP research from a task-agnostic perspective, where methods are reported from various technical views. Specifically, we first introduce the background of MSFP. Next, we review multi-modal and multi-agent fusion methods. A step further, time-series fusion methods are analyzed. In the era of LLM, we also investigate multimodal LLM fusion methods. Finally, we discuss open challenges and future directions for MSFP. We hope this survey can help researchers understand the important progress in MSFP and provide possible insights for future research.

SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between objects, remains underexplored in current 3D vision-language research. Existing datasets often mix semantic cues (e.g., object name) with spatial context, leading models to rely on superficial shortcuts rather than genuinely interpreting spatial relationships. To address this gap, we introduce S\textsc{urprise}3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes. S\textsc{urprise}3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2, including more than 2.8k unique object classes. The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name, thereby mitigating shortcut biases in spatial understanding. These queries comprehensively cover various spatial reasoning skills, such as relative position, narrative perspective, parametric perspective, and absolute distance reasoning. Initial benchmarks demonstrate significant challenges for current state-of-the-art expert 3D visual grounding methods and 3D-LLMs, underscoring the necessity of our dataset and the accompanying 3D Spatial Reasoning Segmentation (3D-SRS) benchmark suite. S\textsc{urprise}3D and 3D-SRS aim to facilitate advancements in spatially aware AI, paving the way for effective embodied interaction and robotic planning. The code and datasets can be found in https://github.com/liziwennba/SUPRISE.

seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic Segmentation

3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. We propose a novel multi-view projection framework that excels in both domain generalization (DG) and unsupervised domain adaptation (UDA). Our approach first aligns Lidar scans into coherent 3D scenes and renders them from multiple virtual camera poses to create a large-scale synthetic 2D dataset (PC2D). We then use it to train a 2D segmentation model in-domain. During inference, the model processes hundreds of views per scene; the resulting logits are back-projected to 3D with an occlusion-aware voting scheme to generate final point-wise labels. Our framework is modular and enables extensive exploration of key design parameters, such as view generation optimization (VGO), visualization modality optimization (MODO), and 2D model choice. We evaluate on the nuScenes and SemanticKITTI datasets under both the DG and UDA settings. We achieve state-of-the-art results in UDA and close to state-of-the-art in DG, with particularly large gains on large, static classes. Our code and dataset generation tools will be publicly available at https://github.com/andrewcaunes/ia4markings

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangScene-X, to unify and generate 3D consistent multi-modality information for reconstruction and understanding. Powered by the generative capability of creating more consistent novel observations, we can build generalizable 3D language-embedded scenes from only sparse views. Specifically, we first train a TriMap video diffusion model that can generate appearance (RGBs), geometry (normals), and semantics (segmentation maps) from sparse inputs through progressive knowledge integration. Furthermore, we propose a Language Quantized Compressor (LQC), trained on large-scale image datasets, to efficiently encode language embeddings, enabling cross-scene generalization without per-scene retraining. Finally, we reconstruct the language surface fields by aligning language information onto the surface of 3D scenes, enabling open-ended language queries. Extensive experiments on real-world data demonstrate the superiority of our LangScene-X over state-of-the-art methods in terms of quality and generalizability. Project Page: https://liuff19.github.io/LangScene-X.

GS4: Generalizable Sparse Splatting Semantic SLAM

Traditional SLAM algorithms are excellent at camera tracking but might generate lower resolution and incomplete 3D maps. Recently, Gaussian Splatting (GS) approaches have emerged as an option for SLAM with accurate, dense 3D map building. However, existing GS-based SLAM methods rely on per-scene optimization which is time-consuming and does not generalize to diverse scenes well. In this work, we introduce the first generalizable GS-based semantic SLAM algorithm that incrementally builds and updates a 3D scene representation from an RGB-D video stream using a learned generalizable network. Our approach starts from an RGB-D image recognition backbone to predict the Gaussian parameters from every downsampled and backprojected image location. Additionally, we seamlessly integrate 3D semantic segmentation into our GS framework, bridging 3D mapping and recognition through a shared backbone. To correct localization drifting and floaters, we propose to optimize the GS for only 1 iteration following global localization. We demonstrate state-of-the-art semantic SLAM performance on the real-world benchmark ScanNet with an order of magnitude fewer Gaussians compared to other recent GS-based methods, and showcase our model's generalization capability through zero-shot transfer to the NYUv2 and TUM RGB-D datasets.

Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments

The robust interpretation of 3D environments is crucial for human-robot collaboration (HRC) applications, where safety and operational efficiency are paramount. Semantic segmentation plays a key role in this context by enabling a precise and detailed understanding of the environment. Considering the intense data hunger for real-world industrial annotated data essential for effective semantic segmentation, this paper introduces a pioneering approach in the Sim2Real domain adaptation for semantic segmentation of 3D point cloud data, specifically tailored for HRC. Our focus is on developing a network that robustly transitions from simulated environments to real-world applications, thereby enhancing its practical utility and impact on a safe HRC. In this work, we propose a dual-stream network architecture (FUSION) combining Dynamic Graph Convolutional Neural Networks (DGCNN) and Convolutional Neural Networks (CNN) augmented with residual layers as a Sim2Real domain adaptation algorithm for an industrial environment. The proposed model was evaluated on real-world HRC setups and simulation industrial point clouds, it showed increased state-of-the-art performance, achieving a segmentation accuracy of 97.76%, and superior robustness compared to existing methods.