Rob-GS reconstructs 3D scenes from long, pose-free videos by tracking adjacent frames with optical flow and splitting the video into segments when Gaussian visibility drops.
InProceedings of the 28th annual conference on Computer graphics and interactive techniques
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Better Robustness: Pose-Free 3D Gaussian Splatting for Arbitrarily Long Videos
Rob-GS reconstructs 3D scenes from long, pose-free videos by tracking adjacent frames with optical flow and splitting the video into segments when Gaussian visibility drops.