No article text was recorded for this version.
closed-vocabulary constraint (fixed-category limitation)
Version 1 of 1202 papers207 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
- Blog: Towards 3D Objectness Learning in an Open World
- Blog: Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
- Blog: Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction
- Blog: Few-shot 3D Point Cloud Semantic Segmentation
- Blog: Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
- Blog: Cubify Anything: Scaling Indoor 3D Object Detection
- Blog: OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
- Blog: CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
- Blog: EgoLifter: Open-World 3D Segmentation for Egocentric Perception
- Blog: Generating Context-Aware Natural Answers for Questions in 3D Scenes
- Blog: OccGS: Zero-shot 3D Occupancy Reconstruction with Semantic and Geometric-Aware Gaussian Splatting
- Blog: Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
- Blog: Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction
- Blog: HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering
- Blog: PointCLIP V2: Adapting CLIP for Powerful 3D Open-world Learning
- Blog: Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
- Blog: Segment Any 3D Object with Language
- Blog: OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
- Blog: CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
- Blog: Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
- Blog: LERF: Language Embedded Radiance Fields
- Blog: 3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation
- Blog: All in One: Visual-Description-Guided Unified Point Cloud Segmentation
- Blog: Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
- Blog: Auto-Vocabulary Segmentation for LiDAR Points
- Blog: 3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation
- Blog: AiDe: Improving 3D Open-Vocabulary Semantic Segmentation by Aligned Vision-Language Learning
- Blog: EA3D: Online Open-World 3D Object Extraction from Streaming Videos
- Blog: Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
- Blog: Towards Learning to Complete Anything in Lidar
- Blog: Advancements in 3D vision understanding using multimodal large language models
- Blog: Better Call SAL: Towards Learning to Segment Anything in Lidar
- Blog: Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
- Blog: Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks
- Blog: RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
- Blog: Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance
- Blog: Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning
- Blog: Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant
- Blog: ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
- Blog: Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding
- Blog: Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloud
- Blog: Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs
- Blog: Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
- Blog: Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
- Blog: OpenGround: Active Cognition-based Reasoning for Open-World 3D Visual Grounding
- Blog: UniPLV: Towards Label-Efficient Open-World 3D Scene Understanding by Regional Visual Language Supervision
- Blog: Language-driven Open-Vocabulary 3D Scene Understanding
- Blog: Detect Anything 3D in the Wild
- Blog: OpenMask3D: Open-Vocabulary 3D Instance Segmentation
- Blog: PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models
- Blog: RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
- Blog: RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation
- Blog: Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
- Blog: Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
- Blog: Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
- Blog: Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image
- Blog: Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models
- Blog: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
- Blog: CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning
Showing 60 of 202 papers.
History & citation
Current · Permanent link
- Open Vocabulary 3D Object Detection with Foundation Models merged into this direction (87% overlap)
- Lifting Vision Language Embeddings for 3D Scene Understanding merged into this direction (88% overlap)
- Language-Grounded 3D Scene Parsing via Cross-Modal Feature Alignment merged into this direction (65% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_closed_vocabulary_constraint_fixed_categ_6876dbca,
title = {closed-vocabulary constraint (fixed-category limitation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/closed-vocabulary-constraint-fixed-category-limitation/rdr_6876dbca24c14bef8473c0e3a1957a21},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_closed_vocabulary_constraint_fixed_categ_6876dbca_v1,
title = {closed-vocabulary constraint (fixed-category limitation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/closed-vocabulary-constraint-fixed-category-limitation/rdr_6876dbca24c14bef8473c0e3a1957a21/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}