2 citations · 4 across the 13 of their papers we have counts for
14 papers
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
Jaewoo Jung, Hyeonseo Yu, Honggyu An +10
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effe…
Geometric Action Model for Robot Policy Learning
Jisang Han, Seonghu Jeon, Jaewoo Jung +7
Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent vision-language-acti…
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
Mungyeom Kim, Minkyeong Jeon, Honggyu An +10
Dynamic scene reconstruction from monocular video remains a fundamental challenge in computer vision. Existing feed-forward methods predict 3D Gaussians pixel-wise for each frame,…
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
Jisu Nam, Jahyeok Koo, Soowon Son +4
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motio…
Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
Jisang Han, Sunghwan Hong, Jaewoo Jung +5
Reliable 3D reconstruction from in-the-wild image collections is often hindered by "noisy" images-irrelevant inputs with little or no view overlap with others. While traditional St…
Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
Soowon Son, Honggyu An, Jisu Nam +7
Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for ro…
C3G: Learning Compact 3D Representations with 2K Gaussians
Honggyu An, Jaewoo Jung, Mungyeom Kim +10
Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3…
Visual Representation Alignment for Multimodal Large Language Models
Heeji Yoon, Jaewoo Jung, Junwan Kim +10
Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tas…
DUSt3R: Enhancing 3D Reconstruction for Dynamic Scenes
Jisang Han, Honggyu An, Jaewoo Jung +7
In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DU…
Cross-View Completion Models are Zero-shot Correspondence Estimators
Honggyu An, Jinhyeon Kim, Seonghoon Park +4
In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate t…
Local All-Pair Correspondence for Point Tracking
Seokju Cho, Jiahui Huang, Jisu Nam +3
We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely…
Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
Jaewoo Jung, Jisang Han, Honggyu An +3
3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurat…
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation
Jiuhn Song, Seonghoon Park, Honggyu An +4
Neural radiance fields (NeRF) shows powerful performance in novel view synthesis and 3D geometry reconstruction, but it suffers from critical performance degradation when the numbe…
MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation
Jongbeom Baek, Gyeongnyeon Kim, Seonghoon Park +3
We propose MaskingDepth, a novel semi-supervised learning framework for monocular depth estimation to mitigate the reliance on large ground-truth depth quantities. MaskingDepth is…