7 papers · 1 filter
HINT: Hierarchical Interaction Modeling for Autoregressive Multi-Human Motion Generation
Mengge Liu, Yan Di, Gu Wang +4
Text-driven multi-human motion generation with complex interactions remains a challenging problem. Despite progress in performance, existing offline methods that generate fixed-len…
Street Gaussians without 3D Object Tracker
Ruida Zhang, Chengxi Li, Chenyangguang Zhang +5
Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object…
4D Gaussian Splatting SLAM
Yanyan Li, Youxu Fang, Zunjie Zhu +3
Simultaneously localizing camera poses and constructing Gaussian radiance fields in dynamic scenes establish a crucial bridge between 2D images and the 4D real world. Instead of re…
MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction
Chenfeng Hou, Qi Xun Yeo, Mengqi Guo +3
3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to…
SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images
Yanyan Li, Yixin Fang, Federico Tombari +1
Sparse Multi-view Images can be Learned to predict explicit radiance fields via Generalizable Gaussian Splatting approaches, which can achieve wider application prospects in real-l…
GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering
Yanyan Li, Chenyu Lyu, Yan Di +3
During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved, especially in non-textured region…