Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Analogical Trajectory Transfer
Junho Kim, Eun Sun Lee, Gwangtak Bae +2
We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location in another. Such a capacity w…
cs.CV2025
Learning 3D Scene Analogies with Neural Contextual Scene Maps
Junho Kim, Gwangtak Bae, Eun Sun Lee +1
Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to compre…
cs.CV2024
I-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM
Gwangtak Bae, Changwoon Choi, Hyeongjun Heo +2
We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios. Casual video captures often suffer f…