5 papers
Efficient Encoder-Free Fourier-based 3D Large Multimodal Model
Guofeng Mei, Wei Lin, Luigi Riz +3
Large Multimodal Models (LMMs) that process 3D data typically rely on heavy, pre-trained visual encoders to extract geometric features. While recent 2D LMMs have begun to eliminate…
GGPT: Geometry Grounded Point Transformer
Yutong Chen, Yiming Wang, Xucong Zhang +2
Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer…
Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
Yiming Wang, Shaofei Wang, Marko Mihajlovic +1
3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D a…
Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting
Yiming Wang, Lucy Chai, Xuan Luo +5
Recent advances in feed-forward 3D Gaussian Splatting have led to rapid improvements in efficient scene reconstruction from sparse views. However, most existing approaches construc…
SplatFormer: Point Transformer for Robust 3D Gaussian Splatting
Yutong Chen, Marko Mihajlovic, Xiyi Chen +3
3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. However, rendering quality significan…