AdpSplit adaptively splits Gaussians using pixel-error statistics to reduce 3DGS training time by 9-22% without quality loss.
Title resolution pending
9 Pith papers cite this work, alongside 823 external citations. Polarity classification is still indexing.
9
Pith papers citing it
823
external citations · external index
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 9roles
background 3polarities
background 3representative citing papers
LEGS improves 3D Gaussian Splatting by replacing first-order edge guidance with second-order Laplacian structural guidance and nonlinear pixel-wise weighting, yielding up to 1.68 dB PSNR gain over baseline 3DGS on Tanks&Temples and Mip-NeRF360.
Pxform provides 102,007 semantic-part 3D editing pairs; PartFlow, a mask-free feedforward editor trained on them, reports the best geometry and appearance editing scores on two benchmarks.
Kinematics-GS reparameterizes Gaussian shapes along motion trajectories with a kinematic prior to reconstruct dynamic 3D scenes from blurry monocular videos by separating dynamic and static components and using coarse-to-fine optimization.
Proposes a reliability-aware frequency modeling framework using geometry-guided detail-demand prior and frequency-aware reliability map to guide high-frequency detail injection in low-resolution 3DGS, with a unified optimization scheme that improves fidelity on benchmarks.
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
TwinOR creates dynamic photorealistic digital twins of operating rooms that generate realistic RGB and depth data enabling embodied AI perception and localization tasks to match real-world performance levels.
The SoccerNet 2026 Challenges benchmarked 427 teams across five soccer video understanding tasks, with leading submissions improving over baselines on all tasks.
citing papers explorer
-
AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
AdpSplit adaptively splits Gaussians using pixel-error statistics to reduce 3DGS training time by 9-22% without quality loss.
-
LEGS: Laplacian-Enhanced Gaussian Splatting with a Nonlinear Weighted Loss
LEGS improves 3D Gaussian Splatting by replacing first-order edge guidance with second-order Laplacian structural guidance and nonlinear pixel-wise weighting, yielding up to 1.68 dB PSNR gain over baseline 3DGS on Tanks&Temples and Mip-NeRF360.
-
Feedforward 3D Editing Learns from Semantic-Part Transformation
Pxform provides 102,007 semantic-part 3D editing pairs; PartFlow, a mask-free feedforward editor trained on them, reports the best geometry and appearance editing scores on two benchmarks.
-
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
Kinematics-GS reparameterizes Gaussian shapes along motion trajectories with a kinematic prior to reconstruct dynamic 3D scenes from blurry monocular videos by separating dynamic and static components and using coarse-to-fine optimization.
-
ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution
Proposes a reliability-aware frequency modeling framework using geometry-guided detail-demand prior and frequency-aware reliability map to guide high-frequency detail injection in low-resolution 3DGS, with a unified optimization scheme that improves fidelity on benchmarks.
-
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
-
Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
-
TwinOR: Photorealistic Digital Twins of Dynamic Operating Rooms for Embodied AI Research
TwinOR creates dynamic photorealistic digital twins of operating rooms that generate realistic RGB and depth data enabling embodied AI perception and localization tasks to match real-world performance levels.
-
SoccerNet 2026 Challenges Results
The SoccerNet 2026 Challenges benchmarked 427 teams across five soccer video understanding tasks, with leading submissions improving over baselines on all tasks.