5 citations · 8 across the 10 of their papers we have counts for
6 papers · 1 filter
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…
LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds
Jaehun Bang, Jinhyeok Kim, Minji Kim +2
Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-…
Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
Sangjune Park, Inhyeok Choi, Donghyeon Soon +2
Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Exis…
VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction
Junsu Kim, Junhee Lee, Ukcheol Shin +2
Understanding 3D scenes semantically and spatially is crucial for the safe navigation of robots and autonomous vehicles, aiding obstacle avoidance and accurate trajectory planning.…
DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction
Jaehyeok Shim, Kyungdon Joo
We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predom…
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…