3 citations · 3 across the 4 of their papers we have counts for
4 papers
UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
Inha Lee, Dongjae Jeong, Junhee Lee +1
Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistenc…
The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning
Wonjun Jo, Kwon Byung-Ki, Kim Ji-Yeon +3
LiDAR is a crucial sensor in autonomous driving, commonly used alongside cameras. By exploiting this camera-LiDAR setup and recent advances in image representation learning, prior…
AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
Jaehoon Jang, Inha Lee, Minje Kim +1
Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction.…
ContactGen: Contact-Guided Interactive 3D Human Generation for Partners
Dongjun Gu, Jaehyeok Shim, Jaehoon Jang +2
Among various interactions between humans, such as eye contact and gestures, physical interactions by contact can act as an essential moment in understanding human behaviors. Inspi…