CausalSplat is a framework that integrates vision-language models with 3D scene graphs to disentangle explicit structural perception from implicit logical inference and achieves state of the art performance on reasoning benchmarks while showing strong generalizability on standard referring and open vocabulary 3D segmentation tasks.
Abstract
While 3D Gaussian Splatting (3DGS) has advanced open vocabulary scene understanding, existing methods remain confined to explicit queries. They struggle to interpret implicit intents, complex spatial constraints, and commonsense reasoning required for practical embodied interactions. To address this gap, we introduce the task of reasoning 3D Gaussian segmentation and construct two benchmarks, Causal-LERF and Causal-ScanNet. These benchmarks systematically evaluate commonsense, spatial, affordance, and counterfactual reasoning. Evaluations reveal that current state of the art methods perform poorly on these reasoning challenges. Therefore, we propose CausalSplat, a framework that integrates vision-language models with 3D scene graphs to disentangle explicit structural perception from implicit logical inference. Extensive experiments demonstrate that CausalSplat achieves state of the art performance on our reasoning benchmarks while showing strong generalizability on standard referring and open vocabulary 3D segmentation tasks. Project Page: https://jiayuding031020.github.io/CausalSplat
This work proposes the Disentangled Spatial Reasoner (DiSR), a simple yet effective framework that reconstructs the physical world into structured 3D evidence using off-the-shelf expert perception models and fine-tunes an LLM with LoRA to perform reasoning solely over this explicit geometric evidence.
Haoze Sun, Jie-Quan Cui, Qingshan Xu et al.· 0 citations
While Vision-Language Models (VLMs) excel at semantic understanding, they struggle to comprehend 3D spatial relationships from limited views. Their reliance on implicit geometric encoding often leads to severe hallucinations and inconsistencies in spatial reasoning tasks. To address this, we introduce GeoMind, a model-then-reason framework that employs a single LLM to autoregressively generate an explicit Geometric Description Language (GDL) map, serving as a grounded context to derive the final answer. This intermediate GDL map provides an explicit and queryable world representation. Leveraging this explicit representation, we enforce a strict referential constraint, compelling the model to ground reasoning solely on the instantiated entities to ensure referential integrity and auditability. Specifically, we lift multi-view observations into object-centric tokens using frozen geometric priors and instance masks. The LLM is trained via a two-stage curriculum with programmatic supervision to generate the GDL map as a prerequisite for answering. On five spatial understanding benchmarks in both image and video settings, GeoMind delivers average accuracy gains of +6.9% (2B) and +9.8% (8B) over Qwen3-VL baselines. Our results suggest that explicit geometric grounding enables robust spatial reasoning without human annotation, providing a scalable and practical route to stronger spatial intelligence in large VLMs.
Xing Wei, Ao-Xiang Tian, Shaofan Liu et al.· Proceedings of the Thirty-Fi...· 0 citations
Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current benchmarks. First, 3D datasets often rely on point clouds that capture geometry but discard rich visual features like texture, text, and materials. Second, annotations treat objects in isolation while ignoring real-world hierarchical organization (scenes, rooms, functional areas, object groups). Third, evaluation tasks focus narrowly on basic recognition rather than multi-step spatial reasoning. In this context, we introduce SceneBench, a benchmark of 966 photorealistic 3D scenes reconstructed with Gaussian Splatting and densely annotated with hierarchical semantics spanning scenes, rooms, functional areas, object groups, and individual objects. These annotations are produced through a human-in-the-loop pipeline combining vision-language models with roughly 1,500 human-hours of iterative refinement and verification, producing over 183K annotated nodes with textual descriptions and 3D bounding boxes. Building on this representation, we define three evaluation tasks: Existence-Based Questions probing object attributes, Spatial Intelligence Questions covering counting, size comparison, distance, and directional relations, and Grounded Question-Reasoning-Answer (QRA) triplets requiring multi-step reasoning across semantic levels. Experiments with state-of-the-art vision-language models show that while models perform well on basic recognition tasks (e.g., up to 85% accuracy for detection), performance drops substantially on hierarchical and compositional reasoning (e.g., down to 60% for counting), revealing limitations not captured by existing benchmarks. SceneBench provides a realistic testbed for developing and evaluating models capable of fine-grained spatial reasoning in photorealistic 3D environments.
Anubhav Khanal, Prabigya Acharya, Roshni Poudel et al.· 0 citations
ZeroSplat lifts 2D Vision-Language Model priors into 3D space through robust multi-view geometric constraints and enables intrinsic point-level understanding without incurring any additional feature storage, and significantly outperforms state-of-the-art methods across generalized and single-target scenarios while maintaining exceptional efficiency.
3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between egocentric and allocentric viewpoints, and at grounding fine-grained appearance. The most common remedies fine-tune the model on large-scale curated spatial-reasoning datasets or attach dedicated encoders for 3D geometry, which typically couples the solution to costly supervision and a specific backbone. We instead introduce GraFT, a training-free framework that supplies the missing 3D structure through a compact, easily maintained 3D scene graph (3DSG). From this 3DSG, GraFT provides three spatial reasoning capabilities: (1) deterministic geometry through symbolic tools, (2) allocentric layout through a bird's-eye-view (BEV) rendering, and (3) visual-attribute grounding through task-relevant egocentric frames. On ScanQA, GraFT improves every metric over the same-backbone baseline, raising CIDEr by 27%. On VSI-Bench, GraFT improves frozen MLLMs by up to 65%, surpassing every proprietary and general-purpose open-source baseline, and several prominent fine-tuned spatial models.
Jun Du, Fernando Ropero, Erkin Turkoz et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
