Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
Gaussian group- ing: Segment and edit anything in 3d scenes
7 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
7
Pith papers citing it
6
external citations · external index
verdicts
UNVERDICTED 7representative citing papers
EPS3D is an end-to-end architecture for 3D panoptic segmentation from multi-view images that uses distillation and semantic-instance mutual enhancement to achieve higher benchmark performance and speed than prior methods.
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
Reconstruction-based 2D inpainters outperform generative ones for 3D consistency in 3DGS object removal; scratch initialization beats finetuning; supported by a new multi-object dataset with ground truth and occlusions.
Fast-SegSim achieves real-time 3D-consistent open-vocabulary segmentation by optimizing feature accumulation in 2D Gaussian Splatting with Precise Tile Intersection and Top-K Hard Selection.
LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.
citing papers explorer
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
EPS3D is an end-to-end architecture for 3D panoptic segmentation from multi-view images that uses distillation and semantic-instance mutual enhancement to achieve higher benchmark performance and speed than prior methods.
-
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
-
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
-
Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
Reconstruction-based 2D inpainters outperform generative ones for 3D consistency in 3DGS object removal; scratch initialization beats finetuning; supported by a new multi-object dataset with ground truth and occlusions.
-
Fast-SegSim: Real-Time Open-Vocabulary Segmentation for Robotics in Simulation
Fast-SegSim achieves real-time 3D-consistent open-vocabulary segmentation by optimizing feature accumulation in 2D Gaussian Splatting with Precise Tile Intersection and Top-K Hard Selection.
-
LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting
LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.