Jie-Ying Lee

BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering

Yi Liu, Jie-Ying Lee, Z Zhangqin Huang, Yu-Lun Liu et autres

Inverse rendering of urban scenes from captured videos enables numerous applications, including content creation and autonomous driving simulation. Physically-based rendering methods follow and control lighting physics, but suffer from reconstruction and rendering artifacts. While generative models produce realistic videos, they offer limited …

BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering

Yi Liu, Jie-Ying Lee, Zheng-Hui Huang, Yu-Lun Liu et autres

Inverse rendering of urban scenes from captured videos enables numerous applications, including content creation and autonomous driving simulation. Physically-based rendering methods follow and control lighting physics, but suffer from reconstruction and rendering artifacts. While generative models produce realistic videos, they offer limited …

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee, Kaipeng Zhang et autres

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? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present …

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee, Kaipeng Zhang et autres

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? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present …

Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion

Ting‐Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee et autres

Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying …

Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion

Ting‐Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee et autres

Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying …

us, tw, in (code pays fourni par la source)

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Jie-Ying Lee, Yi Liu, Wei‐Cheng Chang, C.J. Wu et autres

tw, es, us (code pays fourni par la source)

Lightsout: Diffusion-Based Outpainting for Enhanced Lens Flare Removal

S.‐Y. Tsai, Wei‐Cheng Chang, Jie-Ying Lee, Chen-Ri Su et autres

Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) methods perform poorly when off-frame light sources are incomplete or absent. We propose LightsOut, a diffusion-based outpainting framework tailored …

tw (code pays fourni par la source)

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

C.J. Wu, Y. S. Chen, Jie-Ying Lee, Bo-Hsu Ke et autres

Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360° unbounded scenes. We present AuraFusion360, a novel reference-based method that enables high-quality object removal and hole filling …

tw (code pays fourni par la source)

SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes

Cheng-De Fan, Chen-Wei Chang, Yi Liu, Jie-Ying Lee et autres

We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular scenes. Previous methods extending 3DGS to model dynamic scenes have struggled to represent specular surfaces accurately. Our method addresses …

tw (code pays fourni par la source)

Effect of capping on the Dirac semimetal Cd3As2 on Si grown via molecular beam epitaxy

Wei-Chen Lin, Chiashain Chuang, Chun-Wei Kuo, Meng-Ting Wu et autres

Tunnel field-effect transistor (TFET) is emerging as a promising alternative to overcome the thermionic limit of 60 mV/dec in subthreshold swing (SS) inherent to Metal-Oxide-Semiconductor Field- Effect Transistor (MOSFET) through the band-to-band tunneling (BTBT) mechanism. TFET offers significant potential for applications in …

tw, jp (code pays fourni par la source)

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

C.J. Wu, Y. S. Chen, Jie-Ying Lee, Bo-Hsu Ke et autres

Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360° unbounded scenes. We present AuraFusion360, a novel reference-based method that enables high-quality object removal and hole filling …