C. Stachniss

AdaCropFollow: Self-Supervised Test-Time Adaptation for Visual Under-Canopy Navigation

Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging

A structure-aware merging pipeline that takes per-pixel primitives from any feed-forward method and consolidates them into a compact, content-adaptive Gaussian set while largely retaining visual quality at just $\frac{1}{20}^\text{th}$ of the Gaussians of a per-pixel method is presented.

Robust 6-DoF Object Pose Tracking With Built-In Recovery Under Occlusions and Rapid Object Motions

This paper proposes a novel method that combines efficient learning-based keypoint matching with optimization-based alignment and introduces a novel failure detection and recovery module for robust model-based 6-DoF tracking of unseen objects from RGB-D data.