SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos

Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene graphs. Recently, Vision Language Models (VLM) and Vision Foundation Models (VFM) have demonstrated impressive zero-shot capabilities in a variety of tasks. However, VLMs like Gemini struggle with the dynamics for VidSGG, failing to maintain stable object identities across frames. To overcome this limitation, we propose SAMJAM, a zero-shot pipeline that combines SAM2's temporal tracking with Gemini's semantic understanding. SAM2 also improves upon Gemini's object grounding by producing more accurate bounding boxes. In our method, we first prompt Gemini to generate a frame-level scene graph. Then, we employ a matching algorithm to map each object in the scene graph with a SAM2-generated or SAM2-propagated mask, producing a temporally-consistent scene graph in dynamic environments. Finally, we repeat this process again in each of the following frames. We empirically demonstrate that SAMJAM outperforms Gemini by 8.33% in mean recall on the EPIC-KITCHENS and EPIC-KITCHENS-100 datasets.

ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis

While recent work in scene reconstruction and understanding has made strides in grounding natural language to physical 3D environments, it is still challenging to ground abstract, high-level instructions to a 3D scene. High-level instructions might not explicitly invoke semantic elements in the scene, and even the process of breaking a high-level task into a set of more concrete subtasks, a process called hierarchical task analysis, is environment-dependent. In this work, we propose ASHiTA, the first framework that generates a task hierarchy grounded to a 3D scene graph by breaking down high-level tasks into grounded subtasks. ASHiTA alternates LLM-assisted hierarchical task analysis, to generate the task breakdown, with task-driven 3D scene graph construction to generate a suitable representation of the environment. Our experiments show that ASHiTA performs significantly better than LLM baselines in breaking down high-level tasks into environment-dependent subtasks and is additionally able to achieve grounding performance comparable to state-of-the-art methods.

Domain-Conditioned Scene Graphs for State-Grounded Task Planning

Recent robotic task planning frameworks have integrated large multimodal models (LMMs) such as GPT-4V. To address grounding issues of such models, it has been suggested to split the pipeline into perceptional state grounding and subsequent state-based planning. As we show in this work, the state grounding ability of LMM-based approaches is still limited by weaknesses in granular, structured, domain-specific scene understanding. To address this shortcoming, we develop a more structured state grounding framework that features a domain-conditioned scene graph as its scene representation. We show that such representation is actionable in nature as it is directly mappable to a symbolic state in classical planning languages such as PDDL. We provide an instantiation of our state grounding framework where the domain-conditioned scene graph generation is implemented with a lightweight vision-language approach that classifies domain-specific predicates on top of domain-relevant object detections. Evaluated across three domains, our approach achieves significantly higher state estimation accuracy and task planning success rates compared to the previous LMM-based approaches.

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving

Recent advancements in Vision-Language Models (VLMs) have demonstrated strong potential for autonomous driving tasks. However, their spatial understanding and reasoning-key capabilities for autonomous driving-still exhibit significant limitations. Notably, none of the existing benchmarks systematically evaluate VLMs' spatial reasoning capabilities in driving scenarios. To fill this gap, we propose NuScenes-SpatialQA, the first large-scale ground-truth-based Question-Answer (QA) benchmark specifically designed to evaluate the spatial understanding and reasoning capabilities of VLMs in autonomous driving. Built upon the NuScenes dataset, the benchmark is constructed through an automated 3D scene graph generation pipeline and a QA generation pipeline. The benchmark systematically evaluates VLMs' performance in both spatial understanding and reasoning across multiple dimensions. Using this benchmark, we conduct extensive experiments on diverse VLMs, including both general and spatial-enhanced models, providing the first comprehensive evaluation of their spatial capabilities in autonomous driving. Surprisingly, the experimental results show that the spatial-enhanced VLM outperforms in qualitative QA but does not demonstrate competitiveness in quantitative QA. In general, VLMs still face considerable challenges in spatial understanding and reasoning.

PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks

In Scene Graphs Generation (SGG) one extracts structured representation from visual inputs in the form of objects nodes and predicates connecting them. This facilitates image-based understanding and reasoning for various downstream tasks. Although fully supervised SGG approaches showed steady performance improvements, they suffer from a severe training bias. This is caused by the availability of only small subsets of curated data and exhibits long-tail predicate distribution issues with a lack of predicate diversity adversely affecting downstream tasks. To overcome this, we introduce PRISM-0, a framework for zero-shot open-vocabulary SGG that bootstraps foundation models in a bottom-up approach to capture the whole spectrum of diverse, open-vocabulary predicate prediction. Detected object pairs are filtered and passed to a Vision Language Model (VLM) that generates descriptive captions. These are used to prompt an LLM to generate fine-andcoarse-grained predicates for the pair. The predicates are then validated using a VQA model to provide a final SGG. With the modular and dataset-independent PRISM-0, we can enrich existing SG datasets such as Visual Genome (VG). Experiments illustrate that PRIMS-0 generates semantically meaningful graphs that improve downstream tasks such as Image Captioning and Sentence-to-Graph Retrieval with a performance on par to the best fully supervised methods.

GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction

Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large models such as Segment Anything (SAM) offer strong performance in 2D image segmentation. These advances do not translate directly to performance in the physical 3D world, where they often over-segment objects and fail to produce consistent mask correspondences across views. In this paper, we present GraphSeg, a framework for generating consistent 3D object segmentations from a sparse set of 2D images of the environment without any depth information. GraphSeg adds edges to graphs and constructs dual correspondence graphs: one from 2D pixel-level similarities and one from inferred 3D structure. We formulate segmentation as a problem of edge addition, then subsequent graph contraction, which merges multiple 2D masks into unified object-level segmentations. We can then leverage \emph{3D foundation models} to produce segmented 3D representations. GraphSeg achieves robust segmentation with significantly fewer images and greater accuracy than prior methods. We demonstrate state-of-the-art performance on tabletop scenes and show that GraphSeg enables improved performance on downstream robotic manipulation tasks. Code available at https://github.com/tomtang502/graphseg.git.

Visual Environment-Interactive Planning for Embodied Complex-Question Answering

This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based on the perception of the visual environment. Existing methods often generate plans in a once-for-all manner, i.e., one-step planning. Such approach rely on large models, without sufficient understanding of the environment. Considering multi-step planning, the framework for formulating plans in a sequential manner is proposed in this paper. To ensure the ability of our framework to tackle complex questions, we create a structured semantic space, where hierarchical visual perception and chain expression of the question essence can achieve iterative interaction. This space makes sequential task planning possible. Within the framework, we first parse human natural language based on a visual hierarchical scene graph, which can clarify the intention of the question. Then, we incorporate external rules to make a plan for current step, weakening the reliance on large models. Every plan is generated based on feedback from visual perception, with multiple rounds of interaction until an answer is obtained. This approach enables continuous feedback and adjustment, allowing the robot to optimize its action strategy. To test our framework, we contribute a new dataset with more complex questions. Experimental results demonstrate that our approach performs excellently and stably on complex tasks. And also, the feasibility of our approach in real-world scenarios has been established, indicating its practical applicability.

Gen-C: Populating Virtual Worlds with Generative Crowds

Over the past two decades, researchers have made significant advancements in simulating human crowds, yet these efforts largely focus on low-level tasks like collision avoidance and a narrow range of behaviors such as path following and flocking. However, creating compelling crowd scenes demands more than just functional movement-it requires capturing high-level interactions between agents, their environment, and each other over time. To address this issue, we introduce Gen-C, a generative model to automate the task of authoring high-level crowd behaviors. Gen-C bypasses the labor-intensive and challenging task of collecting and annotating real crowd video data by leveraging a large language model (LLM) to generate a limited set of crowd scenarios, which are subsequently expanded and generalized through simulations to construct time-expanded graphs that model the actions and interactions of virtual agents. Our method employs two Variational Graph Auto-Encoders guided by a condition prior network: one dedicated to learning a latent space for graph structures (agent interactions) and the other for node features (agent actions and navigation). This setup enables the flexible generation of dynamic crowd interactions. The trained model can be conditioned on natural language, empowering users to synthesize novel crowd behaviors from text descriptions. We demonstrate the effectiveness of our approach in two scenarios, a University Campus and a Train Station, showcasing its potential for populating diverse virtual environments with agents exhibiting varied and dynamic behaviors that reflect complex interactions and high-level decision-making patterns.

The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning

Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to guide language models in generating captions. These methods tend to focus on one key aspect of the scene and build a caption that ignores the rest of the visual input. To address this issue, and generate more accurate and complete captions, we propose a novel progressive multi-granularity textual prompting strategy for zero-shot video captioning. Our approach constructs three distinct memory banks, encompassing noun phrases, scene graphs of noun phrases, and entire sentences. Moreover, we introduce a category-aware retrieval mechanism that models the distribution of natural language surrounding the specific topics in question. Extensive experiments demonstrate the effectiveness of our method with 5.7%, 16.2%, and 3.4% improvements in terms of the main metric CIDEr on MSR-VTT, MSVD, and VATEX benchmarks compared to existing state-of-the-art.

Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments

We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours. Existing methods for generating driving simulation environments encode the initial traffic scene as a rasterized image and, as such, require parameter-heavy networks that perform unnecessary computation due to many empty pixels in the rasterized scene. Moreover, we find that existing methods that employ rule-based agent behaviours lack diversity and realism. Scenario Dreamer instead employs a novel vectorized latent diffusion model for initial scene generation that directly operates on the vectorized scene elements and an autoregressive Transformer for data-driven agent behaviour simulation. Scenario Dreamer additionally supports scene extrapolation via diffusion inpainting, enabling the generation of unbounded simulation environments. Extensive experiments show that Scenario Dreamer outperforms existing generative simulators in realism and efficiency: the vectorized scene-generation base model achieves superior generation quality with around 2x fewer parameters, 6x lower generation latency, and 10x fewer GPU training hours compared to the strongest baseline. We confirm its practical utility by showing that reinforcement learning planning agents are more challenged in Scenario Dreamer environments than traditional non-generative simulation environments, especially on long and adversarial driving environments.