Problem
Research questions and friction points this paper is trying to address.
3D Gaussian Splatting
novel-view synthesis
camera pose
VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization
🤖 AI Summary
本文提出VoxelTTO方法，通过优化3D高斯点云生成和相机姿态估计，解决现有3D高斯点云渲染中几何不准确和视角合成失真的问题。
📝 Abstract
Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifacts, while inaccuracies in predicted camera poses can lead to misalignment in novel-view synthesis (NVS). We present VoxelTTO, a feed-forward framework for reconstructing geometrically accurate 3DGS scenes from an arbitrary number of images and optional camera parameters. VoxelTTO aggregates dense image features into a global voxel representation and decodes Gaussians from voxel features, breaking the pixel-to-Gaussian correspondence. To exploit known camera parameters while keeping the pretrained visual foundation model (VFM) parameters frozen, we introduce test-time optimization (TTO) that adapts lightweight LoRA modules using pose supervision. We further replace vanilla 3DGS rasterization with stochastic solid volume rendering during training and inference, improving geometric fidelity. Training updates only the voxel-aligned Gaussian reconstruction modules, requiring 80 GPU hours. Experiments on Replica, Tanks and Temples, and DTU demonstrate improved RGB-D NVS and camera-pose estimation relative to prior methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
VoxelTTO
test-time optimization (TTO)
stochastic solid volume rendering
voxel-aligned Gaussian reconstruction
🔎 Similar Papers
No similar papers found.
