No article text was recorded for this version.
fine-grained spatial discrimination
Version 1 of 134 papers38 conceptsfrozen 2026-10-04
Papers in this version
- Blog: ScanRefer: 3D Object Localization in RGB-D Scans Using Natural Language
- Blog: 3D Spatial Understanding in MLLMs: Disambiguation and Evaluation
- Blog: 3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering
- Blog: Segment-Level and Category-Oriented Network for Knowledge-Based Referring Expression Comprehension
- Blog: Generating Context-Aware Natural Answers for Questions in 3D Scenes
- Blog: Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions
- Blog: Weakly-Supervised 3D Visual Grounding Based on Visual Language Alignment
- Blog: Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
- Blog: OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
- Blog: 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
- Blog: A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
- Blog: DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding
- Blog: Learning Grasp Strategies with Partial Shape Information
- Blog: Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
- Blog: Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding
- Blog: Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
- Blog: Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
- Blog: ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
- Blog: Towards Automatic Animated Storyboarding
- Blog: ReferSplat: Referring Segmentation in 3D Gaussian Splatting
- Blog: Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception
- Blog: DDPA-3DVG: Vision-Language Dual-Decoupling and Progressive Alignment for 3D Visual Grounding
- Blog: C3VQG: Category Consistent Cyclic Visual Question Generation
- Blog: ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
- Blog: 3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment
- Blog: 3DRefTransformer: Fine-Grained Object Identification in Real-World Scenes Using Natural Language
- Blog: LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning
- Blog: HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
- Blog: Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding
- Blog: Data-Efficient 3D Visual Grounding via Order-Aware Referring
- Blog: 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
- Blog: M3DBench: Towards Omni 3D Assistant with Interleaved Multi-modal Instructions
- Blog: Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud
- Blog: AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring
History & citation
Current · Permanent link
- This direction split from Spatial Relational Reasoning for 3D Visual Grounding (65% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_fine_grained_spatial_discrimination_a7ec2713,
title = {fine-grained spatial discrimination},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fine-grained-spatial-discrimination/rdr_a7ec2713c96240939e3b25a8323bf789},
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_fine_grained_spatial_discrimination_a7ec2713_v1,
title = {fine-grained spatial discrimination},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fine-grained-spatial-discrimination/rdr_a7ec2713c96240939e3b25a8323bf789/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}