8 papers · 1 filter
BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering
Yi-Ruei Liu, Jie-Ying Lee, Zheng-Hui Huang +2
Inverse rendering of urban scenes from captured videos enables numerous applications, including content creation and autonomous driving simulation. Physically-based rendering metho…
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion
Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu +10
Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging fo…
YoCausal: How Far is Video Generation from World Model? A Causality Perspective
You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee +3
As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existin…
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
Shr-Ruei Tsai, Wei-Cheng Chang, Jie-Ying Lee +2
Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) met…
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai +6
Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in t…
AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
Chung-Ho Wu, Yang-Jung Chen, Ying-Huan Chen +8
Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometri…
SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes
Cheng-De Fan, Chen-Wei Chang, Yi-Ruei Liu +4
We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular s…
BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes
Chih-Hai Su, Chih-Yao Hu, Shr-Ruei Tsai +3
While Neural Radiance Fields (NeRFs) have demonstrated exceptional quality, their protracted training duration remains a limitation. Generalizable and MVS-based NeRFs, although cap…