The reviewed record of science sign in
Pith

arxiv: 2403.11401 · v2 · pith:X3WBVDHP · submitted 2024-03-18 · cs.CV · cs.AI

Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning

Reviewed by Pithpith:X3WBVDHPopen to challenge →

classification cs.CV cs.AI
keywords scene-llmmodelvisualego-centricfeaturesinformationinteractiveplanning
0
0 comments X
read the original abstract

This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D visual feature representation, that incorporates dense spatial information and supports scene state updates. The model employs a projection layer to efficiently project these features in the pre-trained textual embedding space, enabling effective interpretation of 3D visual information. Unique to our approach is the integration of both scene-level and ego-centric 3D information. This combination is pivotal for interactive planning, where scene-level data supports global planning and ego-centric data is important for localization. Notably, we use ego-centric 3D frame features for feature alignment, an efficient technique that enhances the model's ability to align features of small objects within the scene. Our experiments with Scene-LLM demonstrate its strong capabilities in dense captioning, question answering, and interactive planning. We believe Scene-LLM advances the field of 3D visual understanding and reasoning, offering new possibilities for sophisticated agent interactions in indoor settings.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 24 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models

    cs.CV 2026-05 unverdicted novelty 8.0

    Flame3D enables zero-shot compositional 3D scene reasoning by representing scenes as editable visual-textual memories exposed to agentic MLLMs through composable and synthesizable spatial tools.

  2. 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

    cs.CV 2026-04 unverdicted novelty 8.0

    3D-VCD reduces hallucinations in 3D-LLM embodied agents by contrasting predictions from original and distorted 3D scene representations at inference time.

  3. Sentinel: Embodied Cooperative Spatial Reasoning and Planning

    cs.CV 2026-05 unverdicted novelty 7.0

    Introduces Sentinel Challenge benchmark and CoSaR framework for cooperative spatial reasoning and planning among 3-5 decentralized embodied agents across 14 city-scale scenes.

  4. ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    ArchSIBench is a new benchmark dataset and evaluation suite that measures vision-language models on architectural spatial intelligence across 17 subtasks, showing most models lag human baselines especially in transfor...

  5. SpatialMosaic: A Multiview VLM Dataset for Partial Visibility

    cs.CV 2025-12 unverdicted novelty 7.0

    SpatialMosaic introduces a 2M-pair multi-view QA dataset and 1M-pair benchmark for MLLMs on spatial reasoning under partial visibility, plus a hybrid baseline that integrates 3D reconstruction models as geometry encoders.

  6. SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

    cs.AI 2025-11 unverdicted novelty 7.0

    SpatialBench creates a five-level framework and 15-task benchmark to measure hierarchical spatial reasoning in MLLMs, finding strong basic perception but weak symbolic reasoning, causal inference, and planning.

  7. POMA-3D: The Point Map Way to 3D Scene Understanding

    cs.CV 2025-11 unverdicted novelty 7.0

    POMA-3D learns self-supervised 3D scene representations from point maps and improves performance on geometric 3D tasks including navigation and scene retrieval.

  8. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    cs.CV 2026-07 unverdicted novelty 6.0

    ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.

  9. CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

    cs.CV 2026-07 conditional novelty 6.0

    A topology-aware 3D-LLM with hierarchical masked attention and geometric bias outperforms prior 3D-LLMs on a new multi-room scene understanding benchmark built from HM3D.

  10. Context-Aware Explanations for Spatialized Document Layouts

    cs.HC 2026-06 unverdicted novelty 6.0

    CAPE produces spatially grounded natural-language explanations for document layouts using pattern detection and multi-level context, rated more helpful than content-only baselines in a user study.

  11. Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    Occ-VLM reconstructs 3D occupancy from 2D images via a single encoder to ground vision-language reasoning, claiming SOTA occupancy prediction and parity with 3D-input VLMs on VQA and captioning.

  12. PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.

  13. Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    GASP injects geometric priors into VLMs via a deep-supervised correspondence head trained on video point correspondences and depth consistency, raising internal matching accuracy and delivering gains on spatial benchm...

  14. EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy

    cs.CV 2026-05 unverdicted novelty 6.0

    EgoProx benchmark shows MLLMs have some spatial knowledge but struggle to leverage it for egocentric 3D proximity reasoning VQA.

  15. Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.

  16. Assessing VLM-Driven Semantic-Affordance Inference for Non-Humanoid Robot Morphologies

    cs.RO 2026-04 unverdicted novelty 6.0

    VLMs generalize affordance inference to non-humanoid robots but produce inconsistent results with a conservative bias of low false positives and high false negatives, especially for novel object manipulations.

  17. Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM

    cs.CV 2026-03 unverdicted novelty 6.0

    Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five...

  18. Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations

    cs.CV 2026-03 unverdicted novelty 6.0

    GR3D turns 3D scene geometry into ID-indexed text references, enabling zero-shot MLLM spatial reasoning gains of 9% on VSI-Bench and 12% on MindCube.

  19. SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving

    cs.CV 2025-12 conditional novelty 6.0

    SpaceDrive integrates 3D positional encodings derived from depth and ego-states into VLMs, replacing digit tokens to improve spatial reasoning and trajectory regression in autonomous driving.

  20. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0

    Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.

  21. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0

    Spatial-MLLM boosts MLLM spatial intelligence from 2D inputs via dual encoders initialized from geometry models plus space-aware sampling, claiming state-of-the-art results.

  22. Unified 3D Scene Understanding Through Physical World Modeling

    cs.CV 2026-05 unverdicted novelty 5.0

    A probabilistic graphical model called 3WM unifies 3D vision tasks into one system that performs them zero-shot by selecting different inference pathways through multimodal scene nodes.

  23. SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

    cs.RO 2025-01 unverdicted novelty 5.0

    SpatialVLA adds 3D-aware position encoding and adaptive discretized action grids to visual-language-action models, enabling strong zero-shot performance and fine-tuning on new robot setups after pre-training on 1.1 mi...

  24. Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment

    cs.CV 2026-04 unverdicted novelty 4.0

    Geometric Reward Credit Assignment disentangles rewards to geometric tokens and adds reprojection consistency to boost 3D keypoint accuracy from 0.64 to 0.93 and bounding box IoU to 0.686 on a ShapeNetCore benchmark w...