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.
Structure-from-motion revisited
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
SCARED-C corrects robot-kinematics pose errors in the SCARED dataset via COLMAP structure-from-motion followed by keyframe-based scale recovery, producing 17,135 reliable RGB-D pairs.
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.
-
SCARED-C: Corrected Camera Poses for Endoscopic Depth Estimation
SCARED-C corrects robot-kinematics pose errors in the SCARED dataset via COLMAP structure-from-motion followed by keyframe-based scale recovery, producing 17,135 reliable RGB-D pairs.