Reading Group

좋은 논문을 많이 읽어야 좋은 논문을 쓸 수 있습니다. 이를 위해 연구실 구성원들이 번갈아가며 논문을 읽고 소개합니다. Robot Perception, SLAM, World Model 등 Spatial Estimation과 관련된 분야를 중점적으로 다룰 수 있으나 분야에 제한은 없습니다. 근본적인 이론부터 최신 기술 트렌드 습득과 연구자로서 필수적인 논리적 설득력과 비판적 사고를 기르는 것을 목표로 합니다.

2026.08.21

AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model

Paper Slide Page
2026.08.14

NeRF: Representing Scenesas Neural Radiance Fields for View Synthesis

Paper Slide Page Code

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

Paper Slide Page

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Paper Slide
2026.07.31

Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling

Paper Slide Code

𝜋3: Permutation-Equivariant Visual Geometry Learning

Paper Slide Code Page
2026.07.24

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

Paper Slide Code

MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Paper Slide Code Page
2026.07.16

VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction

Paper Slide Code
2026.07.09

Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization

Paper Slide Page

OpenVINS: A Research Platform for Visual-Inertial Estimation

Paper Slide Code Page

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction

Paper Slide Code Page
2026.07.01

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

Paper Slide Code Page
2026.06.26

SLAM-Former: Putting SLAM into One Transformer

Paper Slide Code Page