Search Results for author: Gwangtak Bae

Found 3 papers, 0 papers with code

Learning 3D Scene Analogies with Neural Contextual Scene Maps

no code implementations20 Mar 2025 Junho Kim, Gwangtak Bae, Eun Sun Lee, Young Min Kim

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments.

Imitation Learning Object Rearrangement

I$^2$-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM

no code implementations16 Jul 2024 Gwangtak Bae, Changwoon Choi, Hyeongjun Heo, Sang Min Kim, Young Min Kim

We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios.

Cannot find the paper you are looking for? You can Submit a new open access paper.