Reconstructing unbounded outdoor scenes from sparse outward-facing views poses significant challenges due to minimal view overlap. Previous methods often lack cross-scene understanding and their primitive-centric formulations overload local features to compensate for missing global context, resulting in blurriness in unseen parts of the scene. We propose sshELF, a fast, single-shot pipeline for sparse-view 3D scene reconstruction via hierarchal extrapolation of latent features. Our key insights is that disentangling information extrapolation from primitive decoding allows efficient transfer of structural patterns across training scenes. Our method: (1) learns cross-scene priors to generate intermediate virtual views to extrapolate to unobserved regions, (2) offers a two-stage network design separating virtual view generation from 3D primitive decoding for efficient training and modular model design, and (3) integrates a pre-trained foundation model for joint inference of latent features and texture, improving scene understanding and generalization. sshELF can reconstruct 360 degree scenes from six sparse input views and achieves competitive results on synthetic and real-world datasets. We find that sshELF faithfully reconstructs occluded regions, supports real-time rendering, and provides rich latent features for downstream applications. The code will be released.
We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated scenes with 5.6M mask-text pairs, significantly larger than existing datasets. Building upon this data, we propose Mosaic3D, a foundation model combining a 3D encoder trained with contrastive learning and a lightweight mask decoder for open-vocabulary 3D semantic and instance segmentation. Our approach achieves state-of-the-art results on open-vocabulary 3D semantic and instance segmentation tasks including ScanNet200, Matterport3D, and ScanNet++, with ablation studies validating the effectiveness of our large-scale training data.
The preservation of aquatic biodiversity is critical in mitigating the effects of climate change. Aquatic scene understanding plays a pivotal role in aiding marine scientists in their decision-making processes. In this paper, we introduce AquaticCLIP, a novel contrastive language-image pre-training model tailored for aquatic scene understanding. AquaticCLIP presents a new unsupervised learning framework that aligns images and texts in aquatic environments, enabling tasks such as segmentation, classification, detection, and object counting. By leveraging our large-scale underwater image-text paired dataset without the need for ground-truth annotations, our model enriches existing vision-language models in the aquatic domain. For this purpose, we construct a 2 million underwater image-text paired dataset using heterogeneous resources, including YouTube, Netflix, NatGeo, etc. To fine-tune AquaticCLIP, we propose a prompt-guided vision encoder that progressively aggregates patch features via learnable prompts, while a vision-guided mechanism enhances the language encoder by incorporating visual context. The model is optimized through a contrastive pretraining loss to align visual and textual modalities. AquaticCLIP achieves notable performance improvements in zero-shot settings across multiple underwater computer vision tasks, outperforming existing methods in both robustness and interpretability. Our model sets a new benchmark for vision-language applications in underwater environments. The code and dataset for AquaticCLIP are publicly available on GitHub at xxx.
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.
Human instance segmentation is a core problem for human-centric scene understanding and segmenting human instances poses a unique challenge to vision systems due to large intra-class variations in both appearance and shape, and complicated occlusion patterns. In this paper, we propose a new pose-aware human instance segmentation method. Compared to the previous pose-aware methods which first predict bottom-up poses and then estimate instance segmentation on top of predicted poses, our method integrates both top-down and bottom-up cues for an instance: it adopts detection results as human proposals and jointly estimates human pose and instance segmentation for each proposal. We develop a modular recurrent deep network that utilizes pose estimation to refine instance segmentation in an iterative manner. Our refinement modules exploit pose cues in two levels: as a coarse shape prior and local part attention. We evaluate our approach on two public multi-person benchmarks: OCHuman dataset and COCOPersons dataset. The proposed method surpasses the state-of-the-art methods on OCHuman dataset by 3.0 mAP and on COCOPersons by 6.4 mAP, demonstrating the effectiveness of our approach.
The recent advancements in visual reasoning capabilities of large multimodal models (LMMs) and the semantic enrichment of 3D feature fields have expanded the horizons of robotic capabilities. These developments hold significant potential for bridging the gap between high-level reasoning from LMMs and low-level control policies utilizing 3D feature fields. In this work, we introduce LMM-3DP, a framework that can integrate LMM planners and 3D skill Policies. Our approach consists of three key perspectives: high-level planning, low-level control, and effective integration. For high-level planning, LMM-3DP supports dynamic scene understanding for environment disturbances, a critic agent with self-feedback, history policy memorization, and reattempts after failures. For low-level control, LMM-3DP utilizes a semantic-aware 3D feature field for accurate manipulation. In aligning high-level and low-level control for robot actions, language embeddings representing the high-level policy are jointly attended with the 3D feature field in the 3D transformer for seamless integration. We extensively evaluate our approach across multiple skills and long-horizon tasks in a real-world kitchen environment. Our results show a significant 1.45x success rate increase in low-level control and an approximate 1.5x improvement in high-level planning accuracy compared to LLM-based baselines. Demo videos and an overview of LMM-3DP are available at https://lmm-3dp-release.github.io.
Compositional Zero-Shot Learning (CZSL) aims to recognize subtle differences in meaning or the combination of states and objects through the use of known and unknown concepts during training. Existing methods either focused on prompt configuration or on using prompts to tune the pre-trained Vision-Language model. However, these methods faced challenges in accurately identifying subtle differences in meaning or combining states with objects. To jointly eradicate the above issues and construct an efficient and effective CZSL technique, we suggest a method to improve attribute recognition performance by utilizing diverse Prompt Learning with an Inter/Intra-Modality Fusion Synthesizer in scene understanding involving subtle semantic differences and multiple objects.
Object removal is of great significance to 3D scene understanding, essential for applications in content filtering and scene editing. Current mainstream methods primarily focus on removing individual objects, with a few methods dedicated to eliminating an entire area or all objects of a certain category. They however confront the challenge of insufficient granularity and flexibility for real-world applications, where users demand tailored excision and preservation of objects within defined zones. In addition, most of the current methods require kinds of priors when addressing multi-view inpainting, which is time-consuming. To address these limitations, we propose an efficient and user-friendly pipeline for 3D multi-object removal, enabling users to flexibly select areas and define objects for removal or preservation. Concretely, to ensure object consistency and correspondence across multiple views, we propose a novel mask matching and refinement module, which integrates homography-based warping with high-confidence anchor points for segmentation. By leveraging the IoU joint shape context distance loss, we enhance the accuracy of warped masks and improve subsequent inpainting processes. Considering the current immaturity of 3D multi-object removal, we provide a new evaluation dataset to bridge the developmental void. Experimental results demonstrate that our method significantly reduces computational costs, achieving processing speeds more than 80% faster than state-of-the-art methods while maintaining equivalent or higher reconstruction quality.
In this work, we focus on Weakly Supervised Spatio-Temporal Video Grounding (WSTVG). It is a multimodal task aimed at localizing specific subjects spatio-temporally based on textual queries without bounding box supervision. Motivated by recent advancements in multi-modal foundation models for grounding tasks, we first explore the potential of state-of-the-art object detection models for WSTVG. Despite their robust zero-shot capabilities, our adaptation reveals significant limitations, including inconsistent temporal predictions, inadequate understanding of complex queries, and challenges in adapting to difficult scenarios. We propose CoSPaL (Contextual Self-Paced Learning), a novel approach which is designed to overcome these limitations. CoSPaL integrates three core components: (1) Tubelet Phrase Grounding (TPG), which introduces spatio-temporal prediction by linking textual queries to tubelets; (2) Contextual Referral Grounding (CRG), which improves comprehension of complex queries by extracting contextual information to refine object identification over time; and (3) Self-Paced Scene Understanding (SPS), a training paradigm that progressively increases task difficulty, enabling the model to adapt to complex scenarios by transitioning from coarse to fine-grained understanding.
Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 10,002 entries of interleaved video-image-text data, categorized into four major domains: physical object properties, physical object relationships, physical scene understanding, and physics-based dynamics, further divided into 19 subclasses and 8 distinct capability dimensions. Our extensive experiments, conducted on 75 representative VLMs, reveal that while these models excel in common-sense reasoning, they struggle with understanding the physical world -- likely due to the absence of physical knowledge in their training data and the lack of embedded physical priors. To tackle the shortfall, we introduce PhysAgent, a novel framework that combines the generalization strengths of VLMs with the specialized expertise of vision models, significantly enhancing VLMs' physical understanding across a variety of tasks, including an 18.4\% improvement on GPT-4o. Furthermore, our results demonstrate that enhancing VLMs' physical world understanding capabilities can help embodied agents such as MOKA. We believe that PhysBench and PhysAgent offer valuable insights and contribute to bridging the gap between VLMs and physical world understanding.
Fiducial markers are widely used in various robotics tasks, facilitating enhanced navigation, object recognition, and scene understanding. Despite their advantages for robots and Augmented Reality (AR) applications, they often disrupt the visual aesthetics of environments because they are visible to humans, making them unsuitable for non-intrusive use cases. To address this gap, this paper presents "iMarkers"-innovative, unobtrusive fiducial markers detectable exclusively by robots equipped with specialized sensors. These markers offer high flexibility in production, allowing customization of their visibility range and encoding algorithms to suit various demands. The paper also introduces the hardware designs and software algorithms developed for detecting iMarkers, highlighting their adaptability and robustness in the detection and recognition stages. Various evaluations have demonstrated the effectiveness of iMarkers compared to conventional (printed) and blended fiducial markers and confirmed their applicability in diverse robotics scenarios.
As communication systems transition from symbol transmission to conveying meaningful information, sixth-generation (6G) networks emphasize semantic communication. This approach prioritizes high-level semantic information, improving robustness and reducing redundancy across modalities like text, speech, and images. However, traditional semantic communication faces limitations, including static coding strategies, poor generalization, and reliance on task-specific knowledge bases that hinder adaptability. To overcome these challenges, we propose a novel system combining scene understanding, Large Language Models (LLMs), and open channel coding, named \textbf{OpenSC}. Traditional systems rely on fixed domain-specific knowledge bases, limiting their ability to generalize. Our open channel coding approach leverages shared, publicly available knowledge, enabling flexible, adaptive encoding. This dynamic system reduces reliance on static task-specific data, enhancing adaptability across diverse tasks and environments. Additionally, we use scene graphs for structured semantic encoding, capturing object relationships and context to improve tasks like Visual Question Answering (VQA). Our approach selectively encodes key semantic elements, minimizing redundancy and improving transmission efficiency. Experimental results show significant improvements in both semantic understanding and efficiency, advancing the potential of adaptive, generalizable semantic communication in 6G networks.
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.
Mapping and localization are crucial problems in robotics and autonomous driving. Recent advances in 3D Gaussian Splatting (3DGS) have enabled precise 3D mapping and scene understanding by rendering photo-realistic images. However, existing 3DGS methods often struggle to accurately reconstruct a 3D map that reflects the actual scale and geometry of the real world, which degrades localization performance. To address these limitations, we propose a novel 3DGS method called Geometry-Aware Gaussian Splatting (GeomGS). This method fully integrates LiDAR data into 3D Gaussian primitives via a probabilistic approach, as opposed to approaches that only use LiDAR as initial points or introduce simple constraints for Gaussian points. To this end, we introduce a Geometric Confidence Score (GCS), which identifies the structural reliability of each Gaussian point. The GCS is optimized simultaneously with Gaussians under probabilistic distance constraints to construct a precise structure. Furthermore, we propose a novel localization method that fully utilizes both the geometric and photometric properties of GeomGS. Our GeomGS demonstrates state-of-the-art geometric and localization performance across several benchmarks, while also improving photometric performance.
Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications such as scene understanding, 3D content generation, and robotics. Despite significant research progress, a thorough review of recent innovations, applications, and challenges is lacking. This survey compiles key theoretical advancements and alternative representations and investigates emerging challenges. It further explores applications on reconstruction, highlights NeRFs' impact on computer vision and robotics, and reviews essential datasets and toolkits. By identifying gaps in the literature, this survey discusses open challenges and offers directions for future research.
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.
Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current approaches use distinct methods tailored to sub-tasks such as Situation Recognition and detection of Human-Human and Human-Object Interactions. However, recent advances in image understanding have often leveraged web-scale vision-language (V&L) representations to obviate task-specific engineering. In this work, we propose a framework for dynamic scene understanding tasks by leveraging knowledge from modern, frozen V&L representations. By framing these tasks in a generic manner - as predicting and parsing structured text, or by directly concatenating representations to the input of existing models - we achieve state-of-the-art results while using a minimal number of trainable parameters relative to existing approaches. Moreover, our analysis of dynamic knowledge of these representations shows that recent, more powerful representations effectively encode dynamic scene semantics, making this approach newly possible.
4D panoptic LiDAR segmentation is essential for scene understanding in autonomous driving and robotics, combining semantic and instance segmentation with temporal consistency. Current methods, like 4D-PLS and 4D-STOP, use a tracking-by-detection methodology, employing deep learning networks to perform semantic and instance segmentation on each frame. To maintain temporal consistency, large-size instances detected in the current frame are compared and associated with instances within a temporal window that includes the current and preceding frames. However, their reliance on short-term instance detection, lack of motion estimation, and exclusion of small-sized instances lead to frequent identity switches and reduced tracking performance. We address these issues with the NextStop1 tracker, which integrates Kalman filter-based motion estimation, data association, and lifespan management, along with a tracklet state concept to improve prioritization. Evaluated using the LiDAR Segmentation and Tracking Quality (LSTQ) metric on the SemanticKITTI validation set, NextStop demonstrated enhanced tracking performance, particularly for small-sized objects like people and bicyclists, with fewer ID switches, earlier tracking initiation, and improved reliability in complex environments. The source code is available at https://github.com/AIROTAU/NextStop
Scene understanding in remote sensing often faces challenges in generating accurate representations for complex environments such as various land use areas or coastal regions, which may also include snow, clouds, or haze. To address this, we present a vision-language framework named Spectral LLaVA, which integrates multispectral data with vision-language alignment techniques to enhance scene representation and description. Using the BigEarthNet v2 dataset from Sentinel-2, we establish a baseline with RGB-based scene descriptions and further demonstrate substantial improvements through the incorporation of multispectral information. Our framework optimizes a lightweight linear projection layer for alignment while keeping the vision backbone of SpectralGPT frozen. Our experiments encompass scene classification using linear probing and language modeling for jointly performing scene classification and description generation. Our results highlight Spectral LLaVA's ability to produce detailed and accurate descriptions, particularly for scenarios where RGB data alone proves inadequate, while also enhancing classification performance by refining SpectralGPT features into semantically meaningful representations.