Predicting future dynamics is crucial for applications like autonomous driving and robotics, where understanding the environment is key. Existing pixel-level methods are computationally expensive and often focus on irrelevant details. To address these challenges, we introduce $\texttt{DINO-Foresight}$, a novel framework that operates in the semantic feature space of pretrained Vision Foundation Models (VFMs). Our approach trains a masked feature transformer in a self-supervised manner to predict the evolution of VFM features over time. By forecasting these features, we can apply off-the-shelf, task-specific heads for various scene understanding tasks. In this framework, VFM features are treated as a latent space, to which different heads attach to perform specific tasks for future-frame analysis. Extensive experiments show that our framework outperforms existing methods, demonstrating its robustness and scalability. Additionally, we highlight how intermediate transformer representations in $\texttt{DINO-Foresight}$ improve downstream task performance, offering a promising path for the self-supervised enhancement of VFM features. We provide the implementation code at https://github.com/Sta8is/DINO-Foresight .
Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning, Emma-X. Emma-X leverages our constructed hierarchical embodiment dataset based on BridgeV2, containing 60,000 robot manipulation trajectories auto-annotated with grounded task reasoning and spatial guidance. Additionally, we introduce a trajectory segmentation strategy based on gripper states and motion trajectories, which can help mitigate hallucination in grounding subtask reasoning generation. Experimental results demonstrate that Emma-X achieves superior performance over competitive baselines, particularly in real-world robotic tasks requiring spatial reasoning.
3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While the vanilla Gaussian Splatting representation is mainly designed for view synthesis, more recent works investigated how to extend it with scene understanding and language features. However, existing methods lack a detailed comprehension of scenes, limiting their ability to segment and interpret complex structures. To this end, We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural Gaussians to learn instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of what we call Super-Gaussians. Super-Gaussians facilitate the distillation of 2D language features into 3D space. Through Super-Gaussians, our method enables high-dimensional language feature rendering without extreme increases in GPU memory. Extensive experiments demonstrate that SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks.
The emergence of general human knowledge and impressive logical reasoning capacity in rapidly progressed vision-language models (VLMs) have driven increasing interest in applying VLMs to high-level autonomous driving tasks, such as scene understanding and decision-making. However, an in-depth study on the relationship between knowledge proficiency, especially essential driving expertise, and closed-loop autonomous driving performance requires further exploration. In this paper, we investigate the effects of the depth and breadth of fundamental driving knowledge on closed-loop trajectory planning and introduce WiseAD, a specialized VLM tailored for end-to-end autonomous driving capable of driving reasoning, action justification, object recognition, risk analysis, driving suggestions, and trajectory planning across diverse scenarios. We employ joint training on driving knowledge and planning datasets, enabling the model to perform knowledge-aligned trajectory planning accordingly. Extensive experiments indicate that as the diversity of driving knowledge extends, critical accidents are notably reduced, contributing 11.9% and 12.4% improvements in the driving score and route completion on the Carla closed-loop evaluations, achieving state-of-the-art performance. Moreover, WiseAD also demonstrates remarkable performance in knowledge evaluations on both in-domain and out-of-domain datasets.
We present datasets containing urban traffic and rural road scenes recorded using hyperspectral snap-shot sensors mounted on a moving car. The novel hyperspectral cameras used can capture whole spectral cubes at up to 15 Hz. This emerging new sensor modality enables hyperspectral scene analysis for autonomous driving tasks. Up to the best of the author's knowledge no such dataset has been published so far. The datasets contain synchronized 3-D laser, spectrometer and hyperspectral data. Dense ground truth annotations are provided as semantic labels, material and traversability. The hyperspectral data ranges from visible to near infrared wavelengths. We explain our recoding platform and method, the associated data format along with a code library for easy data consumption. The datasets are publicly available for download.
3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions, relying on inefficient per-scene multi-view optimizations, which are impractical for many real-world tasks. To address this, we propose SLGaussian, a feed-forward method for constructing 3D semantic fields from sparse viewpoints, allowing direct inference of 3DGS-based scenes. By ensuring consistent SAM segmentations through video tracking and using low-dimensional indexing for high-dimensional CLIP features, SLGaussian efficiently embeds language information in 3D space, offering a robust solution for accurate 3D scene understanding under sparse view conditions. In experiments on two-view sparse 3D object querying and segmentation in the LERF and 3D-OVS datasets, SLGaussian outperforms existing methods in chosen IoU, Localization Accuracy, and mIoU. Moreover, our model achieves scene inference in under 30 seconds and open-vocabulary querying in just 0.011 seconds per query.
Multi-object tracking algorithms are deployed in various applications, each with unique performance requirements. For example, track switches pose significant challenges for offline scene understanding, as they hinder the accuracy of data interpretation. Conversely, in online surveillance applications, their impact is often minimal. This disparity underscores the need for application-specific performance evaluations that are both simple and mathematically sound. The trajectory generalized optimal sub-pattern assignment (TGOSPA) metric offers a principled approach to evaluate multi-object tracking performance. It accounts for localization errors, the number of missed and false objects, and the number of track switches, providing a comprehensive assessment framework. This paper illustrates the effective use of the TGOSPA metric in computer vision tasks, addressing challenges posed by the need for application-specific scoring methodologies. By exploring the TGOSPA parameter selection, we enable users to compare, comprehend, and optimize the performance of algorithms tailored for specific tasks, such as target tracking and training of detector or re-ID modules.
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diverse real-world backgrounds and the requirement for maintaining visual naturality. Building upon this challenge, we reformulate physical adversarial attacks as a one-shot patch-generation problem. Our approach generates adversarial patches through a deep generative model that considers the specific scene context, enabling direct physical deployment in matching environments. The primary challenge lies in simultaneously achieving two objectives: generating adversarial patches that effectively mislead object detection systems while determining contextually appropriate placement within the scene. We propose MAGIC (Mastering Physical Adversarial Generation In Context), a novel framework powered by multi-modal LLM agents to address these challenges. MAGIC automatically understands scene context and orchestrates adversarial patch generation through the synergistic interaction of language and vision capabilities. MAGIC orchestrates three specialized LLM agents: The adv-patch generation agent (GAgent) masters the creation of deceptive patches through strategic prompt engineering for text-to-image models. The adv-patch deployment agent (DAgent) ensures contextual coherence by determining optimal placement strategies based on scene understanding. The self-examination agent (EAgent) completes this trilogy by providing critical oversight and iterative refinement of both processes. We validate our method on both digital and physical level, \ie, nuImage and manually captured real scenes, where both statistical and visual results prove that our MAGIC is powerful and effectively for attacking wide-used object detection systems.
The concept of function and affordance is a critical aspect of 3D scene understanding and supports task-oriented objectives. In this work, we develop a model that learns to structure and vary functional affordance across a 3D hierarchical scene graph representing the spatial organization of a scene. The varying functional affordance is designed to integrate with the varying spatial context of the graph. More specifically, we develop an algorithm that learns to construct a 3D hierarchical scene graph (3DHSG) that captures the spatial organization of the scene. Starting from segmented object point clouds and object semantic labels, we develop a 3DHSG with a top node that identifies the room label, child nodes that define local spatial regions inside the room with region-specific affordances, and grand-child nodes indicating object locations and object-specific affordances. To support this work, we create a custom 3DHSG dataset that provides ground truth data for local spatial regions with region-specific affordances and also object-specific affordances for each object. We employ a transformer-based model to learn the 3DHSG. We use a multi-task learning framework that learns both room classification and learns to define spatial regions within the room with region-specific affordances. Our work improves on the performance of state-of-the-art baseline models and shows one approach for applying transformer models to 3D scene understanding and the generation of 3DHSGs that capture the spatial organization of a room. The code and dataset are publicly available.
Scene Graph Generation (SGG) converts visual scenes into structured graph representations, providing deeper scene understanding for complex vision tasks. However, existing SGG models often overlook essential spatial relationships and struggle with generalization in open-vocabulary contexts. To address these limitations, we propose LLaVA-SpaceSGG, a multimodal large language model (MLLM) designed for open-vocabulary SGG with enhanced spatial relation modeling. To train it, we collect the SGG instruction-tuning dataset, named SpaceSGG. This dataset is constructed by combining publicly available datasets and synthesizing data using open-source models within our data construction pipeline. It combines object locations, object relations, and depth information, resulting in three data formats: spatial SGG description, question-answering, and conversation. To enhance the transfer of MLLMs' inherent capabilities to the SGG task, we introduce a two-stage training paradigm. Experiments show that LLaVA-SpaceSGG outperforms other open-vocabulary SGG methods, boosting recall by 8.6% and mean recall by 28.4% compared to the baseline. Our codebase, dataset, and trained models are publicly accessible on GitHub at the following URL: https://github.com/Endlinc/LLaVA-SpaceSGG.
Event cameras, which feature pixels that independently respond to changes in brightness, are becoming increasingly popular in high-speed applications due to their lower latency, reduced bandwidth requirements, and enhanced dynamic range compared to traditional frame-based cameras. Numerous imaging and vision techniques have leveraged event cameras for high-speed scene understanding by capturing high-framerate, high-dynamic range videos, primarily utilizing the temporal advantages inherent to event cameras. Additionally, imaging and vision techniques have utilized the light field-a complementary dimension to temporal information-for enhanced scene understanding. In this work, we propose "Event Fields", a new approach that utilizes innovative optical designs for event cameras to capture light fields at high speed. We develop the underlying mathematical framework for Event Fields and introduce two foundational frameworks to capture them practically: spatial multiplexing to capture temporal derivatives and temporal multiplexing to capture angular derivatives. To realize these, we design two complementary optical setups one using a kaleidoscope for spatial multiplexing and another using a galvanometer for temporal multiplexing. We evaluate the performance of both designs using a custom-built simulator and real hardware prototypes, showcasing their distinct benefits. Our event fields unlock the full advantages of typical light fields-like post-capture refocusing and depth estimation-now supercharged for high-speed and high-dynamic range scenes. This novel light-sensing paradigm opens doors to new applications in photography, robotics, and AR/VR, and presents fresh challenges in rendering and machine learning.
We present Visual Lexicon, a novel visual language that encodes rich image information into the text space of vocabulary tokens while retaining intricate visual details that are often challenging to convey in natural language. Unlike traditional methods that prioritize either high-level semantics (e.g., CLIP) or pixel-level reconstruction (e.g., VAE), ViLex simultaneously captures rich semantic content and fine visual details, enabling high-quality image generation and comprehensive visual scene understanding. Through a self-supervised learning pipeline, ViLex generates tokens optimized for reconstructing input images using a frozen text-to-image (T2I) diffusion model, preserving the detailed information necessary for high-fidelity semantic-level reconstruction. As an image embedding in the language space, ViLex tokens leverage the compositionality of natural languages, allowing them to be used independently as "text tokens" or combined with natural language tokens to prompt pretrained T2I models with both visual and textual inputs, mirroring how we interact with vision-language models (VLMs). Experiments demonstrate that ViLex achieves higher fidelity in image reconstruction compared to text embeddings--even with a single ViLex token. Moreover, ViLex successfully performs various DreamBooth tasks in a zero-shot, unsupervised manner without fine-tuning T2I models. Additionally, ViLex serves as a powerful vision encoder, consistently improving vision-language model performance across 15 benchmarks relative to a strong SigLIP baseline.
4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal dynamic modeling. To address these limitations, we propose a Spatial-Temporal simulAtion for drivinG (Stag-1) model to reconstruct real-world scenes and design a controllable generative network to achieve 4D simulation. Stag-1 constructs continuous 4D point cloud scenes using surround-view data from autonomous vehicles. It decouples spatial-temporal relationships and produces coherent keyframe videos. Additionally, Stag-1 leverages video generation models to obtain photo-realistic and controllable 4D driving simulation videos from any perspective. To expand the range of view generation, we train vehicle motion videos based on decomposed camera poses, enhancing modeling capabilities for distant scenes. Furthermore, we reconstruct vehicle camera trajectories to integrate 3D points across consecutive views, enabling comprehensive scene understanding along the temporal dimension. Following extensive multi-level scene training, Stag-1 can simulate from any desired viewpoint and achieve a deep understanding of scene evolution under static spatial-temporal conditions. Compared to existing methods, our approach shows promising performance in multi-view scene consistency, background coherence, and accuracy, and contributes to the ongoing advancements in realistic autonomous driving simulation. Code: https://github.com/wzzheng/Stag.
Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately placed adversarial texts, such texts are often easily identifiable as anomalous. In this paper, we present the first approach to generate scene-coherent typographic adversarial attacks that mislead advanced LVLMs while maintaining visual naturalness through the capability of the LLM-based agent. Our approach addresses three critical questions: what adversarial text to generate, where to place it within the scene, and how to integrate it seamlessly. We propose a training-free, multi-modal LLM-driven scene-coherent typographic adversarial planning (SceneTAP) that employs a three-stage process: scene understanding, adversarial planning, and seamless integration. The SceneTAP utilizes chain-of-thought reasoning to comprehend the scene, formulate effective adversarial text, strategically plan its placement, and provide detailed instructions for natural integration within the image. This is followed by a scene-coherent TextDiffuser that executes the attack using a local diffusion mechanism. We extend our method to real-world scenarios by printing and placing generated patches in physical environments, demonstrating its practical implications. Extensive experiments show that our scene-coherent adversarial text successfully misleads state-of-the-art LVLMs, including ChatGPT-4o, even after capturing new images of physical setups. Our evaluations demonstrate a significant increase in attack success rates while maintaining visual naturalness and contextual appropriateness. This work highlights vulnerabilities in current vision-language models to sophisticated, scene-coherent adversarial attacks and provides insights into potential defense mechanisms.
3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to embodied agents which demands to gradually perceive the scene through progressive embodied exploration. In this paper, we formulate an embodied 3D occupancy prediction task to target this practical scenario and propose a Gaussian-based EmbodiedOcc framework to accomplish it. We initialize the global scene with uniform 3D semantic Gaussians and progressively update local regions observed by the embodied agent. For each update, we extract semantic and structural features from the observed image and efficiently incorporate them via deformable cross-attention to refine the regional Gaussians. Finally, we employ Gaussian-to-voxel splatting to obtain the global 3D occupancy from the updated 3D Gaussians. Our EmbodiedOcc assumes an unknown (i.e., uniformly distributed) environment and maintains an explicit global memory of it with 3D Gaussians. It gradually gains knowledge through the local refinement of regional Gaussians, which is consistent with how humans understand new scenes through embodied exploration. We reorganize an EmbodiedOcc-ScanNet benchmark based on local annotations to facilitate the evaluation of the embodied 3D occupancy prediction task. Experiments demonstrate that our EmbodiedOcc outperforms existing local prediction methods and accomplishes the embodied occupancy prediction with high accuracy and strong expandability. Code: https://github.com/YkiWu/EmbodiedOcc.
Machine learning-based embedded systems employed in safety-critical applications such as aerospace and autonomous driving need to be robust against perturbations produced by soft errors. Soft errors are an increasing concern in modern digital processors since smaller transistor geometries and lower voltages give electronic devices a higher sensitivity to background radiation. The resilience of deep neural network (DNN) models to perturbations in their parameters is determined, to a large extent, by the structure of the model itself, and also by the selected numerical representation and used arithmetic precision. When compression techniques such as model pruning and model quantization are applied to reduce memory footprint and computational complexity for deployment, both model structure and numerical representation are modified and thus, soft error robustness also changes. In this sense, although the choice of activation functions (AFs) in DNN models is frequently ignored, it conditions not only their accuracy and trainability, but also compressibility rates and numerical robustness. This paper investigates the suitability of using bounded AFs to improve model robustness against DNN parameter perturbations, assessing at the same time the impact of this choice on deployment in terms of model accuracy, compressibility, and computational burden. In particular, we analyze encoder-decoder fully convolutional models aimed at performing semantic segmentation tasks on hyperspectral images for scene understanding in autonomous driving. Deployment characterization is performed experimentally on an AMD-Xilinx's KV260 SoM.
The remarkable success of deep learning methods in solving computer vision problems, such as image classification, object detection, scene understanding, image segmentation, etc., has paved the way for their application in biomedical imaging. One such application is in the field of CT image denoising, whereby deep learning methods are proposed to recover denoised images from noisy images acquired at low radiation. Outputs derived from applying deep learning denoising algorithms may appear clean and visually pleasing; however, the underlying diagnostic image quality may not be on par with their normal-dose CT counterparts. In this work, we assessed the image quality of deep learning denoising algorithms by making use of visual perception- and data fidelity-based task-agnostic metrics (like the PSNR and the SSIM) - commonly used in the computer vision - and a task-based detectability assessment (the LCD) - extensively used in the CT imaging. When compared against normal-dose CT images, the deep learning denoisers outperformed low-dose CT based on metrics like the PSNR (by 2.4 to 3.8 dB) and SSIM (by 0.05 to 0.11). However, based on the LCD performance, the detectability using quarter-dose denoised outputs was inferior to that obtained using normal-dose CT scans.
The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to enhance MLLMs, such as incorporating point cloud features, have been made, yet a considerable gap remains between the models' learned representations and the inherent complexity of 3D scenes. This discrepancy largely stems from the training of MLLMs on predominantly 2D data, which restricts their effectiveness in comprehending 3D spaces. To address this issue, in this paper, we propose a novel generalist model, i.e., Video-3D LLM, for 3D scene understanding. By treating 3D scenes as dynamic videos and incorporating 3D position encoding into these representations, our Video-3D LLM aligns video representations with real-world spatial contexts more accurately. In addition, we have implemented a maximum coverage sampling technique to optimize the trade-off between computational cost and performance. Extensive experiments demonstrate that our model achieves state-of-the-art performance on several 3D scene understanding benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.
Humans naturally interact with their 3D surroundings using language, and modeling 3D language fields for scene understanding and interaction has gained growing interest. This paper introduces ChatSplat, a system that constructs a 3D language field, enabling rich chat-based interaction within 3D space. Unlike existing methods that primarily use CLIP-derived language features focused solely on segmentation, ChatSplat facilitates interaction on three levels: objects, views, and the entire 3D scene. For view-level interaction, we designed an encoder that encodes the rendered feature map of each view into tokens, which are then processed by a large language model (LLM) for conversation. At the scene level, ChatSplat combines multi-view tokens, enabling interactions that consider the entire scene. For object-level interaction, ChatSplat uses a patch-wise language embedding, unlike LangSplat's pixel-wise language embedding that implicitly includes mask and embedding. Here, we explicitly decouple the language embedding into separate mask and feature map representations, allowing more flexible object-level interaction. To address the challenge of learning 3D Gaussians posed by the complex and diverse distribution of language embeddings used in the LLM, we introduce a learnable normalization technique to standardize these embeddings, facilitating effective learning. Extensive experimental results demonstrate that ChatSplat supports multi-level interactions -- object, view, and scene -- within 3D space, enhancing both understanding and engagement.
3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI. Providing a solution to these applications requires a multifaceted approach that covers scene-centric, object-centric, as well as interaction-centric capabilities. While there exist numerous datasets approaching the former two problems, the task of understanding interactable and articulated objects is underrepresented and only partly covered by current works. In this work, we address this shortcoming and introduce (1) an expertly curated dataset in the Universal Scene Description (USD) format, featuring high-quality manual annotations, for instance, segmentation and articulation on 280 indoor scenes; (2) a learning-based model together with a novel baseline capable of predicting part segmentation along with a full specification of motion attributes, including motion type, articulated and interactable parts, and motion parameters; (3) a benchmark serving to compare upcoming methods for the task at hand. Overall, our dataset provides 8 types of annotations - object and part segmentations, motion types, movable and interactable parts, motion parameters, connectivity, and object mass annotations. With its broad and high-quality annotations, the data provides the basis for holistic 3D scene understanding models. All data is provided in the USD format, allowing interoperability and easy integration with downstream tasks. We provide open access to our dataset, benchmark, and method's source code.