BEA-GS achieves superior object boundary segmentation in 3D Gaussian Splatting by introducing two new losses that adjust geometry of visible and non-visible Gaussians based on semantics.
Segment any- thing
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
EmoVerse is a large open-source dataset enabling interpretable visual emotion analysis via B-A-S triplets, region grounding, and unified CES/DES representations created through an MLLM-driven pipeline.
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
Chorus pretrains a shared 3D Gaussian scene encoder via multi-teacher distillation to capture holistic features from high-level semantics to fine-grained structure, with strong transfer on segmentation and point-cloud tasks using far fewer scenes.
GSAL combines diffusion-based visual difficulty scoring with hierarchical semantic coverage to improve active learning retrieval of subtle and rare visual anomalies over standard uncertainty and diversity methods.
Empirical study shows bidirectional but sensitive relationship between compositionality and long-caption understanding in VLMs, promoted by high-quality grounded data and affected by architectural choices like frozen positional embeddings.
citing papers explorer
-
BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
BEA-GS achieves superior object boundary segmentation in 3D Gaussian Splatting by introducing two new losses that adjust geometry of visible and non-visible Gaussians based on semantics.
-
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
-
EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis
EmoVerse is a large open-source dataset enabling interpretable visual emotion analysis via B-A-S triplets, region grounding, and unified CES/DES representations created through an MLLM-driven pipeline.
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
-
Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
Chorus pretrains a shared 3D Gaussian scene encoder via multi-teacher distillation to capture holistic features from high-level semantics to fine-grained structure, with strong transfer on segmentation and point-cloud tasks using far fewer scenes.
-
Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena
GSAL combines diffusion-based visual difficulty scoring with hierarchical semantic coverage to improve active learning retrieval of subtle and rare visual anomalies over standard uncertainty and diversity methods.
-
Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs
Empirical study shows bidirectional but sensitive relationship between compositionality and long-caption understanding in VLMs, promoted by high-quality grounded data and affected by architectural choices like frozen positional embeddings.