Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis
This addresses the problem of improving rendering quality in thermal infrared novel-view synthesis for applications like surveillance or robotics, but it appears incremental as it builds on existing 3D Gaussian Splatting techniques.
The paper tackles novel-view synthesis with thermal infrared images, which suffers from issues like floaters and blur effects, by introducing Veta-GS, a method that uses a view-dependent deformation field and a Thermal Feature Extractor to achieve better performance on the TI-NSD benchmark.
Recently, 3D Gaussian Splatting (3D-GS) based on Thermal Infrared (TIR) imaging has gained attention in novel-view synthesis, showing real-time rendering. However, novel-view synthesis with thermal infrared images suffers from transmission effects, emissivity, and low resolution, leading to floaters and blur effects in rendered images. To address these problems, we introduce Veta-GS, which leverages a view-dependent deformation field and a Thermal Feature Extractor (TFE) to precisely capture subtle thermal variations and maintain robustness. Specifically, we design view-dependent deformation field that leverages camera position and viewing direction, which capture thermal variations. Furthermore, we introduce the Thermal Feature Extractor (TFE) and MonoSSIM loss, which consider appearance, edge, and frequency to maintain robustness. Extensive experiments on the TI-NSD benchmark show that our method achieves better performance over existing methods.