SpaceDG introduces the first large-scale degradation-aware spatial reasoning dataset using 3D Gaussian Splatting synthesis, showing that visual degradations impair MLLM performance but finetuning on the data improves robustness and can exceed human levels under degradation.
Deep multi-scale convolutional neural network for dynamic scene deblurring
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
STGDNet uses synchronized spatial and temporal difference data from the Tianmouc sensor within a recurrent fusion architecture to deblur RGB frames more effectively than prior RGB-only or event-camera methods.
citing papers explorer
-
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
SpaceDG introduces the first large-scale degradation-aware spatial reasoning dataset using 3D Gaussian Splatting synthesis, showing that visual degradations impair MLLM performance but finetuning on the data improves robustness and can exceed human levels under degradation.
-
Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
STGDNet uses synchronized spatial and temporal difference data from the Tianmouc sensor within a recurrent fusion architecture to deblur RGB frames more effectively than prior RGB-only or event-camera methods.