Autonomous driving systems rely on robust 3D scene understanding. Recent advances in Semantic Scene Completion (SSC) for autonomous driving underscore the limitations of RGB-based approaches, which struggle under motion blur, poor lighting, and adverse weather. Event cameras, offering high dynamic range and low latency, address these challenges by providing asynchronous data that complements RGB inputs. We present DSEC-SSC, the first real-world benchmark specifically designed for event-aided SSC, which includes a novel 4D labeling pipeline for generating dense, visibility-aware labels that adapt dynamically to object motion. Our proposed RGB-Event fusion framework, EvSSC, introduces an Event-aided Lifting Module (ELM) that effectively bridges 2D RGB-Event features to 3D space, enhancing view transformation and the robustness of 3D volume construction across SSC models. Extensive experiments on DSEC-SSC and simulated SemanticKITTI-E demonstrate that EvSSC is adaptable to both transformer-based and LSS-based SSC architectures. Notably, evaluations on SemanticKITTI-C demonstrate that EvSSC achieves consistently improved prediction accuracy across five degradation modes and both In-domain and Out-of-domain settings, achieving up to a 52.5% relative improvement in mIoU when the image sensor partially fails. Additionally, we quantitatively and qualitatively validate the superiority of EvSSC under motion blur and extreme weather conditions, where autonomous driving is challenged. The established datasets and our codebase will be made publicly at https://github.com/Pandapan01/EvSSC.
Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting and reasoning about the driving environment. In this paper, we present a unified Driving World Model named HERMES. We seamlessly integrate 3D scene understanding and future scene evolution (generation) through a unified framework in driving scenarios. Specifically, HERMES leverages a Bird's-Eye View (BEV) representation to consolidate multi-view spatial information while preserving geometric relationships and interactions. We also introduce world queries, which incorporate world knowledge into BEV features via causal attention in the Large Language Model (LLM), enabling contextual enrichment for understanding and generation tasks. We conduct comprehensive studies on nuScenes and OmniDrive-nuScenes datasets to validate the effectiveness of our method. HERMES achieves state-of-the-art performance, reducing generation error by 32.4% and improving understanding metrics such as CIDEr by 8.0%. The model and code will be publicly released at https://github.com/LMD0311/HERMES.
Recently, Multimodal Large Language Models (MLLMs) have demonstrated their immense potential in computer-aided diagnosis and decision-making. In the context of robotic-assisted surgery, MLLMs can serve as effective tools for surgical training and guidance. However, there is still a lack of MLLMs specialized for surgical scene understanding in clinical applications. In this work, we introduce EndoChat to address various dialogue paradigms and subtasks in surgical scene understanding that surgeons encounter. To train our EndoChat, we construct the Surg-396K dataset through a novel pipeline that systematically extracts surgical information and generates structured annotations based on collected large-scale endoscopic surgery datasets. Furthermore, we introduce a multi-scale visual token interaction mechanism and a visual contrast-based reasoning mechanism to enhance the model's representation learning and reasoning capabilities. Our model achieves state-of-the-art performance across five dialogue paradigms and eight surgical scene understanding tasks. Additionally, we conduct evaluations with professional surgeons, most of whom provide positive feedback on collaborating with EndoChat. Overall, these results demonstrate that our EndoChat has great potential to significantly advance training and automation in robotic-assisted surgery.
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin technology, offering high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics. This paper systematically reviews recent advances in world models for autonomous driving, proposing a three-tiered taxonomy: (i) Generation of Future Physical World, covering Image-, BEV-, OG-, and PC-based generation methods that enhance scene evolution modeling through diffusion models and 4D occupancy forecasting; (ii) Behavior Planning for Intelligent Agents, combining rule-driven and learning-based paradigms with cost map optimization and reinforcement learning for trajectory generation in complex traffic conditions; (ii) Interaction between Prediction and Planning, achieving multi-agent collaborative decision-making through latent space diffusion and memory-augmented architectures. The study further analyzes training paradigms, including self-supervised learning, multimodal pretraining, and generative data augmentation, while evaluating world models' performance in scene understanding and motion prediction tasks. Future research must address key challenges in self-supervised representation learning, long-tail scenario generation, and multimodal fusion to advance the practical deployment of world models in complex urban environments. Overall, the comprehensive analysis provides a technical roadmap for harnessing the transformative potential of world models in advancing safe and reliable autonomous driving solutions.
Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer significant opportunities for scene understanding but present challenges in interpreting geometry accurately, particularly in the absence of precise ground truth data. To address this, we propose CrossModalityDiffusion, a modular framework designed to generate images across different modalities and viewpoints without prior knowledge of scene geometry. CrossModalityDiffusion employs modality-specific encoders that take multiple input images and produce geometry-aware feature volumes that encode scene structure relative to their input camera positions. The space where the feature volumes are placed acts as a common ground for unifying input modalities. These feature volumes are overlapped and rendered into feature images from novel perspectives using volumetric rendering techniques. The rendered feature images are used as conditioning inputs for a modality-specific diffusion model, enabling the synthesis of novel images for the desired output modality. In this paper, we show that jointly training different modules ensures consistent geometric understanding across all modalities within the framework. We validate CrossModalityDiffusion's capabilities on the synthetic ShapeNet cars dataset, demonstrating its effectiveness in generating accurate and consistent novel views across multiple imaging modalities and perspectives.
Multi-modal Large Language Models (MLLMs) exhibit impressive capabilities in 2D tasks, yet encounter challenges in discerning the spatial positions, interrelations, and causal logic in scenes when transitioning from 2D to 3D representations. We find that the limitations mainly lie in: i) the high annotation cost restricting the scale-up of volumes of 3D scene data, and ii) the lack of a straightforward and effective way to perceive 3D information which results in prolonged training durations and complicates the streamlined framework. To this end, we develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs and construct 3DS-160K , to enhance the pre-training process. Leveraging this high-quality pre-training data, we introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes, showcasing exceptional capability in navigating the complexities of the physical world. 3UR-LLM directly receives 3D point cloud as input and project 3D features fused with text instructions into a manageable set of tokens. Considering the computation burden derived from these hybrid tokens, we design a 3D compressor module to cohesively compress the 3D spatial cues and textual narrative. 3UR-LLM achieves promising performance with respect to the previous SOTAs, for instance, 3UR-LLM exceeds its counterparts by 7.1\% CIDEr on ScanQA, while utilizing fewer training resources. The code and model weights for 3UR-LLM and the 3DS-160K benchmark are available at 3UR-LLM.
Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding. Existing graph-based superpixel segmentation methods typically concentrate on the relationships between a given pixel and its directly adjacent pixels while overlooking the influence of non-adjacent pixels. These approaches do not fully leverage the global information in the graph, leading to suboptimal segmentation quality. To address this limitation, we present SIT-HSS, a hierarchical superpixel segmentation method based on structural information theory. Specifically, we first design a novel graph construction strategy that incrementally explores the pixel neighborhood to add edges based on 1-dimensional structural entropy (1D SE). This strategy maximizes the retention of graph information while avoiding an overly complex graph structure. Then, we design a new 2D SE-guided hierarchical graph partitioning method, which iteratively merges pixel clusters layer by layer to reduce the graph's 2D SE until a predefined segmentation scale is achieved. Experimental results on three benchmark datasets demonstrate that the SIT-HSS performs better than state-of-the-art unsupervised superpixel segmentation algorithms. The source code is available at \url{https://github.com/SELGroup/SIT-HSS}.
Matching objects across partially overlapping camera views is crucial in multi-camera systems and requires a view-invariant feature extraction network. Training such a network with cycle-consistency circumvents the need for labor-intensive labeling. In this paper, we extend the mathematical formulation of cycle-consistency to handle partial overlap. We then introduce a pseudo-mask which directs the training loss to take partial overlap into account. We additionally present several new cycle variants that complement each other and present a time-divergent scene sampling scheme that improves the data input for this self-supervised setting. Cross-camera matching experiments on the challenging DIVOTrack dataset show the merits of our approach. Compared to the self-supervised state-of-the-art, we achieve a 4.3 percentage point higher F1 score with our combined contributions. Our improvements are robust to reduced overlap in the training data, with substantial improvements in challenging scenes that need to make few matches between many people. Self-supervised feature networks trained with our method are effective at matching objects in a range of multi-camera settings, providing opportunities for complex tasks like large-scale multi-camera scene understanding.
Efficiently reconstructing accurate 3D models from monocular video is a key challenge in computer vision, critical for advancing applications in virtual reality, robotics, and scene understanding. Existing approaches typically require pre-computed camera parameters and frame-by-frame reconstruction pipelines, which are prone to error accumulation and entail significant computational overhead. To address these limitations, we introduce VideoLifter, a novel framework that leverages geometric priors from a learnable model to incrementally optimize a globally sparse to dense 3D representation directly from video sequences. VideoLifter segments the video sequence into local windows, where it matches and registers frames, constructs consistent fragments, and aligns them hierarchically to produce a unified 3D model. By tracking and propagating sparse point correspondences across frames and fragments, VideoLifter incrementally refines camera poses and 3D structure, minimizing reprojection error for improved accuracy and robustness. This approach significantly accelerates the reconstruction process, reducing training time by over 82% while surpassing current state-of-the-art methods in visual fidelity and computational efficiency.
Image segmentation is a vital task for providing human assistance and enhancing autonomy in our daily lives. In particular, RGB-D segmentation-leveraging both visual and depth cues-has attracted increasing attention as it promises richer scene understanding than RGB-only methods. However, most existing efforts have primarily focused on semantic segmentation and thus leave a critical gap. There is a relative scarcity of instance-level RGB-D segmentation datasets, which restricts current methods to broad category distinctions rather than fully capturing the fine-grained details required for recognizing individual objects. To bridge this gap, we introduce three RGB-D instance segmentation benchmarks, distinguished at the instance level. These datasets are versatile, supporting a wide range of applications from indoor navigation to robotic manipulation. In addition, we present an extensive evaluation of various baseline models on these benchmarks. This comprehensive analysis identifies both their strengths and shortcomings, guiding future work toward more robust, generalizable solutions. Finally, we propose a simple yet effective method for RGB-D data integration. Extensive evaluations affirm the effectiveness of our approach, offering a robust framework for advancing toward more nuanced scene understanding.
In recent years, 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks. However, their performance in 3D spatial comprehension, which is critical for embodied intelligence, remains limited. Recent advances have leveraged 3D point clouds and multi-view images as inputs, yielding promising results. However, we propose exploring a purely vision-based solution inspired by human perception, which merely relies on visual cues for 3D spatial understanding. This paper empirically investigates the limitations of VLMs in 3D spatial knowledge, revealing that their primary shortcoming lies in the lack of global-local correspondence between the scene and individual frames. To address this, we introduce GPT4Scene, a novel visual prompting paradigm in VLM training and inference that helps build the global-local relationship, significantly improving the 3D spatial understanding of indoor scenes. Specifically, GPT4Scene constructs a 3D Bird's Eye View (BEV) image from the video and marks consistent object IDs across both frames and the BEV image. The model then inputs the concatenated BEV image and video frames with markers. In zero-shot evaluations, GPT4Scene improves performance over closed-source VLMs like GPT-4o. Additionally, we prepare a processed video dataset consisting of 165K text annotation to fine-tune open-source VLMs, achieving state-of-the-art performance on all 3D understanding tasks. Surprisingly, after training with the GPT4Scene paradigm, VLMs consistently improve during inference, even without visual prompting and BEV image as explicit correspondence. It demonstrates that the proposed paradigm helps VLMs develop an intrinsic ability to understand 3D scenes, which paves the way for a noninvasive approach to extending pre-trained VLMs for 3D scene understanding.
We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3D Gaussians and their velocities--in a single forward pass. Our key design is to aggregate 3D Gaussians from all frames using self-supervised scene flows, transforming them to the target timestep to enable complete (i.e., "amodal") reconstructions from arbitrary viewpoints at any moment in time. As an emergent property, STORM automatically captures dynamic instances and generates high-quality masks using only reconstruction losses. Extensive experiments on public datasets show that STORM achieves precise dynamic scene reconstruction, surpassing state-of-the-art per-scene optimization methods (+4.3 to 6.6 PSNR) and existing feed-forward approaches (+2.1 to 4.7 PSNR) in dynamic regions. STORM reconstructs large-scale outdoor scenes in 200ms, supports real-time rendering, and outperforms competitors in scene flow estimation, improving 3D EPE by 0.422m and Acc5 by 28.02%. Beyond reconstruction, we showcase four additional applications of our model, illustrating the potential of self-supervised learning for broader dynamic scene understanding.
Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing the type of driving scenario, actions of risk objects, and driving intentions and suggestions of ego-vehicle. Ultimately, a transformer-based network incorporating a regression token is trained to locate the risk objects. Extensive experiments on the existing DRAMA-ROLISP dataset and the extended DRAMA-SRIS dataset demonstrate that our method is efficient, surpassing many state-of-the-art image-based and video-based methods. Specifically, our method achieves 80.1% BLEU-1 score and 298.5% CIDEr score in the scene understanding task, and 59.6% accuracy in the localization task. Codes and datasets are available at https://github.com/fjq-tongji/MLLM-SUL.
A 3D scene graph represents a compact scene model, storing information about the objects and the semantic relationships between them, making its use promising for robotic tasks. When interacting with a user, an embodied intelligent agent should be capable of responding to various queries about the scene formulated in natural language. Large Language Models (LLMs) are beneficial solutions for user-robot interaction due to their natural language understanding and reasoning abilities. Recent methods for creating learnable representations of 3D scenes have demonstrated the potential to improve the quality of LLMs responses by adapting to the 3D world. However, the existing methods do not explicitly utilize information about the semantic relationships between objects, limiting themselves to information about their coordinates. In this work, we propose a method 3DGraphLLM for constructing a learnable representation of a 3D scene graph. The learnable representation is used as input for LLMs to perform 3D vision-language tasks. In our experiments on popular ScanRefer, RIORefer, Multi3DRefer, ScanQA, Sqa3D, and Scan2cap datasets, we demonstrate the advantage of this approach over baseline methods that do not use information about the semantic relationships between objects. The code is publicly available at https://github.com/CognitiveAISystems/3DGraphLLM.
Autonomous driving in high-speed racing, as opposed to urban environments, presents significant challenges in scene understanding due to rapid changes in the track environment. Traditional sequential network approaches may struggle to meet the real-time knowledge and decision-making demands of an autonomous agent covering large displacements in a short time. This paper proposes a novel baseline architecture for developing sophisticated models capable of true hardware-enabled parallelism, achieving neural processing speeds that mirror the agent's high velocity. The proposed model (Parallel Perception Network (PPN)) consists of two independent neural networks, segmentation and reconstruction networks, running parallelly on separate accelerated hardware. The model takes raw 3D point cloud data from the LiDAR sensor as input and converts it into a 2D Bird's Eye View Map on both devices. Each network independently extracts its input features along space and time dimensions and produces outputs parallelly. The proposed method's model is trained on a system with two NVIDIA T4 GPUs, using a combination of loss functions, including edge preservation, and demonstrates a 2x speedup in model inference time compared to a sequential configuration. Implementation is available at: https://github.com/suwesh/Parallel-Perception-Network. Learned parameters of the trained networks are provided at: https://huggingface.co/suwesh/ParallelPerceptionNetwork.
Monitoring animal populations is crucial for assessing the health of ecosystems. Traditional methods, which require extensive fieldwork, are increasingly being supplemented by time-lapse camera-trap imagery combined with an automatic analysis of the image data. The latter usually involves some object detector aimed at detecting relevant targets (commonly animals) in each image, followed by some postprocessing to gather activity and population data. In this paper, we show that the performance of an object detector in a single frame of a time-lapse sequence can be improved by including spatio-temporal features from the prior frames. We propose a method that leverages temporal information by integrating two additional spatial feature channels which capture stationary and non-stationary elements of the scene and consequently improve scene understanding and reduce the number of stationary false positives. The proposed technique achieves a significant improvement of 24\% in mean average precision ([email omitted]:0.95) over the baseline (temporal feature-free, single frame) object detector on a large dataset of breeding tropical seabirds. We envisage our method will be widely applicable to other wildlife monitoring applications that use time-lapse imaging.
Although multiview fusion has demonstrated potential in LiDAR segmentation, its dependence on computationally intensive point-based interactions, arising from the lack of fixed correspondences between views such as range view and Bird's-Eye View (BEV), hinders its practical deployment. This paper challenges the prevailing notion that multiview fusion is essential for achieving high performance. We demonstrate that significant gains can be realized by directly fusing Polar and Cartesian partitioning strategies within the BEV space. Our proposed BEV-only segmentation model leverages the inherent fixed grid correspondences between these partitioning schemes, enabling a fusion process that is orders of magnitude faster (170$\times$ speedup) than conventional point-based methods. Furthermore, our approach facilitates dense feature fusion, preserving richer contextual information compared to sparse point-based alternatives. To enhance scene understanding while maintaining inference efficiency, we also introduce a hybrid Transformer-CNN architecture. Extensive evaluation on the SemanticKITTI and nuScenes datasets provides compelling evidence that our method outperforms previous multiview fusion approaches in terms of both performance and inference speed, highlighting the potential of BEV-based fusion for LiDAR segmentation. Code is available at \url{https://github.com/skyshoumeng/PC-BEV.}
Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeniable candidates for end-to-end driving systems. However, limited work exists on studying the trustworthiness of DriveVLMs -- a critical factor that directly impacts public transportation safety. In this paper, we introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs), considering diverse perspectives -- including trustfulness, safety, robustness, privacy, and fairness. We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios, comprising over 10k unique scenes and 18k queries. We evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models. Our exhaustive evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats. Specifically, we found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness. DriveVLMs like DriveLM-Agent are particularly vulnerable to disclosing sensitive information. Additionally, both generalist and specialist VLMs remain susceptible to adversarial attacks and struggle to ensure unbiased decision-making across diverse environments and populations. Our findings call for immediate and decisive action to address the trustworthiness of DriveVLMs -- an issue of critical importance to public safety and the welfare of all citizens relying on autonomous transportation systems. Our benchmark is publicly available at \url{https://github.com/taco-group/AutoTrust}, and the leaderboard is released at \url{https://taco-group.github.io/AutoTrust/}.
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from vision-language models. However, current method primarily focus on object-centric representations, supporting object segmentation or detection, while understanding semantic relationships between objects remains largely unexplored. To address this gap, we propose RelationField, the first method to extract inter-object relationships directly from neural radiance fields. RelationField represents relationships between objects as pairs of rays within a neural radiance field, effectively extending its formulation to include implicit relationship queries. To teach RelationField complex, open-vocabulary relationships, relationship knowledge is distilled from multi-modal LLMs. To evaluate RelationField, we solve open-vocabulary 3D scene graph generation tasks and relationship-guided instance segmentation, achieving state-of-the-art performance in both tasks. See the project website at https://relationfield.github.io.
In the field of audio-visual learning, most research tasks focus exclusively on short videos. This paper focuses on the more practical Dense Audio-Visual Event Localization (DAVEL) task, advancing audio-visual scene understanding for longer, untrimmed videos. This task seeks to identify and temporally pinpoint all events simultaneously occurring in both audio and visual streams. Typically, each video encompasses dense events of multiple classes, which may overlap on the timeline, each exhibiting varied durations. Given these challenges, effectively exploiting the audio-visual relations and the temporal features encoded at various granularities becomes crucial. To address these challenges, we introduce a novel CCNet, comprising two core modules: the Cross-Modal Consistency Collaboration (CMCC) and the Multi-Temporal Granularity Collaboration (MTGC). Specifically, the CMCC module contains two branches: a cross-modal interaction branch and a temporal consistency-gated branch. The former branch facilitates the aggregation of consistent event semantics across modalities through the encoding of audio-visual relations, while the latter branch guides one modality's focus to pivotal event-relevant temporal areas as discerned in the other modality. The MTGC module includes a coarse-to-fine collaboration block and a fine-to-coarse collaboration block, providing bidirectional support among coarse- and fine-grained temporal features. Extensive experiments on the UnAV-100 dataset validate our module design, resulting in a new state-of-the-art performance in dense audio-visual event localization. The code is available at https://github.com/zzhhfut/CCNet-AAAI2025.