Pith. sign in

REVIEW 33 cited by

ConceptFusion: Open-set Multimodal 3D Mapping

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.07241 v3 pith:5SRC3FYE submitted 2023-02-14 cs.CV cs.AIcs.RO

classification cs.CVcs.AIcs.RO
keywords conceptsopen-setconceptfusionmapsapproachesmultimodalaudioenabling
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Building 3D maps of the environment is central to robot navigation, planning, and interaction with objects in a scene. Most existing approaches that integrate semantic concepts with 3D maps largely remain confined to the closed-set setting: they can only reason about a finite set of concepts, pre-defined at training time. Further, these maps can only be queried using class labels, or in recent work, using text prompts. We address both these issues with ConceptFusion, a scene representation that is (1) fundamentally open-set, enabling reasoning beyond a closed set of concepts and (ii) inherently multimodal, enabling a diverse range of possible queries to the 3D map, from language, to images, to audio, to 3D geometry, all working in concert. ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio. We demonstrate that pixel-aligned open-set features can be fused into 3D maps via traditional SLAM and multi-view fusion approaches. This enables effective zero-shot spatial reasoning, not needing any additional training or finetuning, and retains long-tailed concepts better than supervised approaches, outperforming them by more than 40% margin on 3D IoU. We extensively evaluate ConceptFusion on a number of real-world datasets, simulated home environments, a real-world tabletop manipulation task, and an autonomous driving platform. We showcase new avenues for blending foundation models with 3D open-set multimodal mapping. For more information, visit our project page https://concept-fusion.github.io or watch our 5-minute explainer video https://www.youtube.com/watch?v=rkXgws8fiDs

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 33 Pith papers

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

  1. Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

    cs.CV 2025-04 conditional novelty 7.0 of 10

    All-Angles Bench, a 2,132-question benchmark across 90 real scenes, shows current MLLMs score around 60% on multi-view understanding while humans score 82%, with the largest gaps in camera pose estimation and cross-vi...

  2. Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

    cs.CV 2025-04 conditional novelty 7.0 of 10

    LOCATE 3D localizes objects named in referring expressions directly from posed RGB-D frames, achieving 61.7% top-1 accuracy at IoU 25 on SR3D/NR3D/ScanRefer and 63.7% when trained with a new 130K-annotation dataset.

  3. 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A feature-diversity-guided token compression pipeline for 3D VLMs keeps 94.7% of original QA accuracy at 128 tokens and runs 1.92x faster than uncompressed LLaVA-3D.

  4. Memory for Attention: Language-Conditioned Re-Perception with a Vision--Language--Motion Map

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Persistent map memory schedules budgeted re-perception better than memoryless VLM priors, with gain equal to Var(√λ), and language-conditioned VLMM needs both open-vocabulary relevance and per-instance dynamics.

  5. Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps

    cs.RO 2026-07 conditional novelty 6.0 of 10

    VLMM is a 3D map representation where each object carries a fused, uncertainty-aware motion attribute (language-based movability prior + observed geometric motion) that makes motion queries such as 'what is moving' an...

  6. Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics

    cs.CV 2026-07 conditional novelty 6.0 of 10

    JITOMA keeps 3D scene graph nodes dormant until a natural-language query activates only task-relevant objects, bounding active graph size and captioning latency while preserving grounding accuracy.

  7. CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding

    cs.CV 2026-07 accept novelty 6.0 of 10

    Training-free closed-form lift plus spatially predictive entropy coding of Gaussian-to-anchor bindings yields sub-megabyte open-vocabulary 3D fields that match or beat prior accuracy.

  8. MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MV-GEL uses a learned view selector and a fine-tuned vision-language segmentation model to localize text-described faces and edges on 3D meshes.

  9. FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning

    cs.CV 2026-04 accept novelty 6.0 of 10

    Joint factor-graph inference over LLM- and geometry-constrained functional edges yields higher recall and substantially lower calibration error than independent pairwise functional scene-graph methods.

  10. VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A vision-language model writes a simulation program—grounded by segmentation and 3D tools—that predicts physically plausible futures from an image and caption, outperforming video generators on modified benchmarks.

  11. From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

    cs.AI 2025-08 conditional novelty 6.0 of 10

    A brain-inspired navigation system stores landmarks, routes, and map-like voxel features in structured spatial memory and uses MLLM-powered retrieval to achieve strong results across object, instance, instruction, and...

  12. Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes

    cs.CV 2025-08 conditional novelty 6.0 of 10

    OVODA combines a 3DETR-style detector with a frozen foundation model to detect novel objects and attributes in 3D scenes, and the OVAD dataset adds spatial and motion attribute labels to nuScenes.

  13. IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A benchmark that scores vision-language models by reconstructing the 3D scene behind an image as executable Blender code finds the models fail mainly on spatial precision, not tool usage.

  14. CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

    cs.RO 2025-06 conditional novelty 6.0 of 10

    CodeDiffuser uses vision-language-model-generated code to build 3D attention maps that condition a diffusion policy, improving success on ambiguous language manipulation tasks compared with end-to-end baselines.

  15. FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding

    cs.CV 2025-06 conditional novelty 6.0 of 10

    FreeQ-Graph builds a semantically aligned 3D scene graph using CLIP, LLaVA, and an LLM, and reports strong zero-shot results on 3D visual grounding, segmentation, and scene graph prediction.

  16. Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Satellite imagery plus population is enough to generate commuting origin-destination flows that closely match models using detailed sociodemographic and point-of-interest data.

  17. Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Embodied VideoAgent augments an LLM-based video agent with persistent object memory built from egocentric video, depth, and pose, plus VLM-based memory updates, reporting gains on Ego4D-VQ3D, OpenEQA, and EnvQA.

  18. GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting

    cs.CV 2024-12 conditional novelty 6.0 of 10

    GAGS achieves strong open-vocabulary 3D localization and segmentation by using depth-aware SAM prompting and an unsupervised granularity factor to distill consistent CLIP features into a single Gaussian feature field.

  19. SLGaussian: Fast Language Gaussian Splatting in Sparse Views

    cs.CV 2024-12 conditional novelty 6.0 of 10

    SLGaussian builds a 3D semantic field from two photos in a single forward pass, stores CLIP features in a memory bank for fast open-vocabulary queries, and reports higher IoU than LangSplat and LERF on the LERF and 3D...

  20. ChatSplat: 3D Conversational Gaussian Splatting

    cs.CV 2024-12 conditional novelty 6.0 of 10

    ChatSplat learns a 3D conversational field in Gaussian Splatting that supports object-, view-, and scene-level chat with an LLM at real-time speeds.

  21. Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Diorama produces a structured, CAD-based 3D scene model from one RGB image using pretrained foundation models and staged layout optimization, with no end-to-end training.

  22. 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning

    cs.CV 2024-11 conditional novelty 6.0 of 10

    3D-Mem represents explored and unexplored regions as compact snapshot images that a vision-language model can reason over, improving embodied question answering and lifelong navigation.

  23. PickScan: Object discovery and reconstruction from handheld interactions

    cs.CV 2024-11 conditional novelty 6.0 of 10

    An interaction-guided, class-agnostic pipeline that discovers and reconstructs each manipulated object as a separate 3D model from egocentric RGB-D video.

  24. OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots

    cs.CV 2025-06 conditional novelty 5.0 of 10

    OV-MAP projects 2D masks into 3D and uses mesh-area voting to create zero-shot, open-vocabulary 3D instance segmentation maps.

  25. ForesightNav: Learning Scene Imagination for Efficient Exploration

    cs.RO 2025-04 conditional novelty 5.0 of 10

    ForesightNav uses a learned imagination module that predicts unseen occupancy and CLIP semantic features from partial maps, then selects navigation goals from the imagined map, improving simulated PointNav and ObjectN...

  26. MR-COGraphs: Communication-efficient Multi-Robot Open-vocabulary Mapping System via 3D Scene Graphs

    cs.RO 2024-12 conditional novelty 5.0 of 10

    A multi-robot mapping system compresses 512-dimensional object semantics to 3 numbers for transmission, cutting map-sharing data by over 80 percent with comparable query accuracy.

  27. BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence

    cs.CV 2024-11 conditional novelty 5.0 of 10

    BIP3D is an image-centric 3D perception model that uses 2D foundation model features with explicit 3D position encoding to beat point-cloud-based methods on the EmbodiedScan detection and grounding benchmarks.

  28. Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A carefully engineered pipeline of 2D grounding, 3D tracking, proposal merging, and Alpha-CLIP classification with a standardized similarity filter achieves state-of-the-art open-vocabulary 3D instance segmentation on...

  29. OpenFusion++: An Open-vocabulary Real-time Scene Understanding System

    cs.CV 2025-04 conditional novelty 4.0 of 10

    OpenFusion++ upgrades the OpenFusion real-time 3D mapping system with confidence-based boundary refinement, area-weighted semantic caching, and a two-stage query matching that improves semantic accuracy and spatial qu...

  30. Human-Robot Dialogue Annotation for Multi-Modal Common Ground

    cs.HC 2024-11 conditional novelty 4.0 of 10

    The authors present and release a multi-layer symbolic annotation of the SCOUT human-robot dialogue corpus, covering utterance semantics, multi-floor dialogue structure, and visual context for common-ground research.

  31. Voxel-Aggregated Feature Synthesis: Efficient Dense Mapping for Simulated 3D Reasoning

    cs.CV 2024-11 conditional novelty 4.0 of 10

    VAFS replaces per-frame embedding in dense 3D mapping with per-object synthetic view embedding, using simulator ground-truth segmentation, achieving faster and higher-IoU semantic maps in simulation.

  32. Gaussian Splatting as a Unified Representation for Autonomy in Unstructured Environments

    cs.RO 2025-05 conditional novelty 2.0 of 10

    Gaussian splatting is advocated as a unified navigation representation, but the experimental support is drawn entirely from the authors' earlier papers.

  33. Multimodal Perception for Goal-oriented Navigation: A Survey

    cs.RO 2025-04 conditional novelty 2.0 of 10

    A literature survey that categorizes multimodal goal-oriented navigation methods into six inference domains and claims this taxonomy reveals cross-task computational patterns.

Pith tools