4 papers
Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals
Zhirui Dai, Hojoon Shin, Yulun Tian +2
Dense reconstruction and differentiable rendering are fundamental tightly connected operations in 3D vision and computer graphics. Recent neural implicit representations demonstrat…
Seeing the Bigger Picture: 3D Latent Mapping for Mobile Manipulation Policy Learning
Sunghwan Kim, Woojeh Chung, Zhirui Dai +5
In this paper, we demonstrate that mobile manipulation policies utilizing a 3D latent map achieve stronger spatial and temporal reasoning than policies relying solely on images. We…
LatentAM: Real-Time, Large-Scale Latent Gaussian Attention Mapping via Online Dictionary Learning
Junwoon Lee, Yulun Tian
We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D observations for open-vocabulary robotic…
MISO: Multiresolution Submap Optimization for Efficient Globally Consistent Neural Implicit Reconstruction
Yulun Tian, Hanwen Cao, Sunghwan Kim +1
Neural implicit representations have had a significant impact on simultaneous localization and mapping (SLAM) by enabling robots to build continuous, differentiable, and high-fidel…