Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

• URL: http://arxiv.org/abs/2512.02487v1
• Date: Tue, 02 Dec 2025 07:22:36 GMT
• Title: Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
• Authors: Yerim Jeon, Miso Lee, WonJun Moon, Jae-Pil Heo,
• Abstract summary: 3D Spatial Language Instruction Mask (3D-SLIM) is an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes.<n>3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks.
• Score: 37.97359376885946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard decoders from language modeling, which rely on a causal attention mask. This design introduces two fundamental conflicts in 3D scene understanding: sequential bias among order-agnostic 3D objects and restricted object-instruction attention, hindering task-specific reasoning. To overcome these limitations, we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes. Our 3D-SLIM introduces two key components: a Geometry-adaptive Mask that constrains attention based on spatial density rather than token order, and an Instruction-aware Mask that enables object tokens to directly access instruction context. This design allows the model to process objects based on their spatial relationships while being guided by the user's task. 3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks. Extensive experiments across multiple benchmarks and LLM baselines validate its effectiveness and underscore the critical role of decoder design in 3D multi-modal reasoning.

Related papers

• Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement [12.260126771415019]
  We introduce Task-Aware 3D Scene-level Affordance segmentation (TASA)<n>TASA is a novel geometry-optimized framework that jointly leverages 2D semantic cues and 3D geometric reasoning in a coarse-to-fine manner.<n>To fully exploit 3D geometric information, a 3D affordance refinement module is proposed to integrate 2D semantic priors with local 3D geometry.
  arXiv  Detail & Related papers  (2025-11-12T13:36:37Z)
• CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D [0.0]
  3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation.<n>Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D class-agnostic masks generated via vision-language models (VLMs)<n>We leverage SemanticSAM with progressive granularity refinement to generate more accurate and numerous object-level masks.
  arXiv  Detail & Related papers  (2025-09-29T09:43:00Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [91.94869042117621]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning.<n>Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation.<n>We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation [72.12250272218792]
  We propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. We integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks. The generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.
  arXiv  Detail & Related papers  (2024-11-20T12:02:12Z)
• Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model [108.35777542298224]
  Reason3D processes point cloud data and text prompts to produce textual responses and segmentation masks.<n>We propose a hierarchical mask decoder that employs a coarse-to-fine approach to segment objects within expansive scenes.
  arXiv  Detail & Related papers  (2024-05-27T17:59:41Z)
• Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers [65.51132104404051]
  We introduce the use of object identifiers and object-centric representations to interact with scenes at the object level. Our model significantly outperforms existing methods on benchmarks including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.
  arXiv  Detail & Related papers  (2023-12-13T14:27:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.