6 papers
GrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
Si-Yu Lu, Yung-Yao Chen, Yi Jan Chen +3
Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric consistency and predict Gaussia…
GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment
Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng +2
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient…
See More, Detect Less? Taming Information Leakage in Multi-View Anomaly Detection
Shang-Fu Chen, Kuan-Chuan Peng, Jhih-Ciang Wu +2
In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-based pipeline, normal cues fro…
OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
Si-Yu Lu, Po-Ting Chen, Hui-Che Hsu +3
Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve impressive reconstruction quality…
DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment
Sheng-Hao Liao, Shang-Fu Chen, Tai-Ming Huang +2
Drag-based image editing using generative models provides intuitive control over image structures. However, existing methods rely heavily on manually provided masks and textual pro…
ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection
Tai-Ming Huang, Wei-Tung Lin, Kai-Lung Hua +3
The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable d…