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.
hub
arXiv preprint arXiv:2306.12156 (2023) 31
33 Pith papers cite this work. Polarity classification is still indexing.
33
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
OpenSGA fuses vision-language, textual, and geometric features via a distance-gated attention encoder and minimum-cost-flow allocator to outperform prior methods on both frame-to-scan and subscan-to-subscan 3D scene graph alignment, backed by a new 700k-sample ScanNet-SG dataset.
LAGO achieves state-of-the-art zero-shot performance with fewer image regions by using class-agnostic object discovery followed by confidence-controlled language-guided refinement and dual-channel aggregation.
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
OmniOVCD uses SAM 3's decoupled outputs and an SFID strategy to achieve state-of-the-art IoU scores of 67.2, 66.5, 24.5, and 27.1 on four OVCD benchmarks, surpassing prior methods.
SegFS is a dual-path architecture that uses sparse keyframe open-vocabulary predictions to condition a fast feature-space network for efficient temporal instance segmentation in videos.
MV-GEL localizes fine-grained geometric entities on 3D meshes from natural language by ranking informative views with GELviews, applying VLM segmentation, and lifting masks via geometry-aware ray casting, reporting up to 1.7X face IoU and 4.5X edge F1 gains over baselines.
FAT decomposes structured prediction into specialist hypothesis generation and foundation-model proxy reasoning, yielding consistent gains over baselines on detection, trajectory, and segmentation tasks.
Presents MMIOC-1M benchmark with 1M+ samples across 14 super-categories and RTVPNet with domain projection, sparse sampling, and bidirectional interaction, claiming SOTA on MMIOC-1M, LVIS, and COCO.
Meridian matches metric-semantic primitives across aerial and ground views for training-free global localization in diverse natural environments, reporting 2.4 m average trajectory error over 19 km.
COTRATE is an online self-supervised framework that uses proprioceptive terrain assessment to supervise visual traversability estimation with alignment loss and diversity-aware replay for continual robot-agnostic learning.
Introduces Embodied Tool Protocol and tool externalization to improve embodied AI performance on perception and cognition tasks, with measured gains but limits on execution capabilities.
InstructSAM uses learnable queries in a VLM to condition SAM3 for single-pass multi-instance segmentation from arbitrary instructions, with a new Inst2Seg benchmark.
RepSAM applies CKA-guided rank allocation in PEFT plus multi-modal fusion to adapt SAM, reaching 97.9% of full fine-tuning mIoU with 158x fewer parameters on robotic benchmarks.
P2DNav proposes a three-part hierarchical framework (panorama-to-downview reasoning, sliding-window dialogue memory, and reflective reorientation) that reports large success-rate gains on the R2R-CE zero-shot VLN benchmark.
SparseSAM achieves 2x faster inference and 2.8x memory reduction in SAM with only 0.004 mIoU loss at 0.4 density via Stripe-Sort Attention and Residual-Consistency MLP.
StateScribe uses a dual-layer memory architecture for episodic scenes and object-centric changes to deliver live and historical descriptions, achieving 83.1% F1 accuracy across revisits in evaluations and user studies with BLV participants.
GRAIL autonomously grounds relational concepts in NeSy-RL by using LLM weak supervision followed by interaction-based refinement, matching or exceeding manually defined concepts on Atari games.
H-SPAM produces accurate, regular, and perfectly nested hierarchical superpixels that outperform prior hierarchical methods and match recent non-hierarchical state-of-the-art.
A deformable soft conical hand is modeled in physics simulation and its scooping trajectories are optimized via evolutionary search, enabling effective contact-rich granular tasks validated in both simulation and physical robot experiments.
AIM-CoT enhances interleaved multimodal chain-of-thought reasoning by adding context-enhanced attention generation, active visual probing via information foraging, and dynamic attention-shift triggering.
Terra produces a lightweight task-agnostic metric-semantic 3D scene graph for outdoor environments using terrain-aware place nodes and hierarchically organized regions.
CucumberVision compares five 3D length methods on 48 RGB-D captures of seven cucumbers and shows a novel medial-axis cubic spline with trapezoidal integration achieves the lowest 4.13% MAPE, outperforming baselines at corrected significance.
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.
-
OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
OpenSGA fuses vision-language, textual, and geometric features via a distance-gated attention encoder and minimum-cost-flow allocator to outperform prior methods on both frame-to-scan and subscan-to-subscan 3D scene graph alignment, backed by a new 700k-sample ScanNet-SG dataset.
-
LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
LAGO achieves state-of-the-art zero-shot performance with fewer image regions by using class-agnostic object discovery followed by confidence-controlled language-guided refinement and dual-channel aggregation.
-
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
-
OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3
OmniOVCD uses SAM 3's decoupled outputs and an SFID strategy to achieve state-of-the-art IoU scores of 67.2, 66.5, 24.5, and 27.1 on four OVCD benchmarks, surpassing prior methods.
-
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
SegFS is a dual-path architecture that uses sparse keyframe open-vocabulary predictions to condition a fast feature-space network for efficient temporal instance segmentation in videos.
-
MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes
MV-GEL localizes fine-grained geometric entities on 3D meshes from natural language by ranking informative views with GELviews, applying VLM segmentation, and lifting masks via geometry-aware ray casting, reporting up to 1.7X face IoU and 4.5X edge F1 gains over baselines.
-
Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning
FAT decomposes structured prediction into specialist hypothesis generation and foundation-model proxy reasoning, yielding consistent gains over baselines on detection, trajectory, and segmentation tasks.
-
InstructSAM: Segment Any Instance with Any Instructions
InstructSAM uses learnable queries in a VLM to condition SAM3 for single-pass multi-instance segmentation from arbitrary instructions, with a new Inst2Seg benchmark.
-
P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation
P2DNav proposes a three-part hierarchical framework (panorama-to-downview reasoning, sliding-window dialogue memory, and reflective reorientation) that reports large success-rate gains on the R2R-CE zero-shot VLN benchmark.
-
SparseSAM: Structured Sparsification of Activations in Segment Anything Models
SparseSAM achieves 2x faster inference and 2.8x memory reduction in SAM with only 0.004 mIoU loss at 0.4 density via Stripe-Sort Attention and Residual-Consistency MLP.
-
H-SPAM: Hierarchical Superpixel Anything Model
H-SPAM produces accurate, regular, and perfectly nested hierarchical superpixels that outperform prior hierarchical methods and match recent non-hierarchical state-of-the-art.
-
Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
CucumberVision compares five 3D length methods on 48 RGB-D captures of seven cucumbers and shows a novel medial-axis cubic spline with trapezoidal integration achieves the lowest 4.13% MAPE, outperforming baselines at corrected significance.
-
ESAM++: Efficient Online 3D Perception on the Edge
ESAM++ introduces a 3D Sparse Feature Pyramid Network for efficient online 3D scene perception on edge devices, claiming competitive accuracy with up to 3x faster inference and 2x smaller model size than ESAM on four benchmarks.
-
RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction
Introduces the largest global aerial road segmentation dataset and RoadGIE, an interactive model using topology-aware prompts that reports SOTA accuracy and connectivity on the new benchmark with a 3.7M parameter network.
-
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
TinySAM 2 reaches 90% of SAM 2.1 performance on DAVIS and SA-V using 7% of the memory tokens and 3% of the training data via frame selection, spatial average pooling, temporal similarity-based token pruning, and a RepViT image encoder.
-
Weight Group-wise Post-Training Quantization for Medical Foundation Model
Permutation-COMQ is a new post-training quantization algorithm that reorders weights within layers and uses only dot-product and rounding steps to deliver the highest reported accuracy for 2-, 4-, and 8-bit medical foundation models.
-
Semantic-Fast-SAM: Efficient Semantic Segmenter
Semantic-Fast-SAM matches prior SAM-based semantic segmentation accuracy on Cityscapes and ADE20K while running about 20 times faster by combining FastSAM with SSA labeling and CLIP for open-vocabulary cases.