GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains on Replica and +2.23 dB on real hardware at fixed budget.
Conceptfusion: Open-set multimodal 3d mapping
11 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
11
Pith papers citing it
4
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 11roles
background 1polarities
background 1representative citing papers
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.
Dynamic scene graphs serve as explicit memory to improve imitation learning policies for spatial-temporal reasoning under partial observability in mobile and tabletop manipulation.
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.
AgentGrounder performs zero-shot 3D visual grounding on colored point clouds via an offline object lookup table and an online agent that selectively retrieves, scores geometrically, and renders images on demand, reporting gains over SeeGround on ScanRefer and Nr3D.
FUS3DMaps fuses voxel- and instance-level open-vocabulary layers inside a shared 3D voxel map to improve both layers and enable scalable accurate semantic mapping.
MV3DIS uses 3D-guided mask matching and depth consistency to produce more consistent multi-view 2D masks that refine into accurate zero-shot 3D instances.
Survey organizing VLM-based social robot navigation into reasoning, planning, and bridging components with a proposed roadmap for hybrid deployable systems.
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 while preserving 2D performance.
citing papers explorer
-
GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping
GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains on Replica and +2.23 dB on real hardware at fixed budget.
-
MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes
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.
-
Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
Dynamic scene graphs serve as explicit memory to improve imitation learning policies for spatial-temporal reasoning under partial observability in mobile and tabletop manipulation.
-
ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
-
SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
-
Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models
Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.
-
AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models
AgentGrounder performs zero-shot 3D visual grounding on colored point clouds via an offline object lookup table and an online agent that selectively retrieves, scores geometrically, and renders images on demand, reporting gains over SeeGround on ScanRefer and Nr3D.
-
FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers
FUS3DMaps fuses voxel- and instance-level open-vocabulary layers inside a shared 3D voxel map to improve both layers and enable scalable accurate semantic mapping.
-
MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation
MV3DIS uses 3D-guided mask matching and depth consistency to produce more consistent multi-view 2D masks that refine into accurate zero-shot 3D instances.
-
Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control
Survey organizing VLM-based social robot navigation into reasoning, planning, and bridging components with a proposed roadmap for hybrid deployable systems.
-
Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
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 while preserving 2D performance.