1 citations · 1 across the 7 of their papers we have counts for
8 papers
Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering
Ruei-Chi Lai, Bolivar Solarte, Chin-Hsuan Wu +2
Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answeri…
uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images
Jonathan Lee, Bolivar Solarte, Chin-Hsuan Wu +4
We present uLayout, a unified model for estimating room layout geometries from both perspective and panoramic images, whereas traditional solutions require different model designs…
CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
Kai He, Chin-Hsuan Wu, Igor Gilitschenski
Recent advances in 3D representations, such as Neural Radiance Fields and 3D Gaussian Splatting, have greatly improved realistic scene modeling and novel-view synthesis. However, a…
Self-training Room Layout Estimation via Geometry-aware Ray-casting
Bolivar Solarte, Chin-Hsuan Wu, Jin-Cheng Jhang +3
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casti…
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
Chin-Hsuan Wu, Yen-Chun Chen, Bolivar Solarte +2
We present iFusion, a novel 3D object reconstruction framework that requires only two views with unknown camera poses. While single-view reconstruction yields visually appealing re…
360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
Bolivar Solarte, Chin-Hsuan Wu, Yueh-Cheng Liu +2
We present 360-MLC, a self-training method based on multi-view layout consistency for finetuning monocular room-layout models using unlabeled 360-images only. This can be valuable…