7 papers
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
Yujie Guo, Yudong Jin, Lingteng Qiu +7
Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity g…
JOintGS: Joint Optimization of Cameras, Bodies and 3D Gaussians for In-the-Wild Monocular Reconstruction
Zihan Lou, Jinlong Fan, Sihan Ma +2
Reconstructing high-fidelity animatable 3D human avatars from monocular RGB videos remains challenging, particularly in unconstrained in-the-wild scenarios where camera parameters…
GP-GS: Gaussian Processes Densification for 3D Gaussian Splatting
Zhihao Guo, Jingxuan Su, Chenghao Qian +8
3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we pr…
InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting
Jinlong Fan, Shanshan Zhao, Liang Zheng +3
Reconstructing complete and animatable 3D human avatars from monocular videos remains challenging, particularly under severe occlusions. While 3D Gaussian Splatting has enabled pho…
FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction
Jinlong Fan, Bingyu Hu, Xingguang Li +2
Reconstructing high-fidelity animatable human avatars from monocular videos remains challenging due to insufficient geometric information in single-view observations. While recent…
Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field
Jinlong Fan, Xuepu Zeng, Jing Zhang +3
Dynamic scene representation and reconstruction have undergone transformative advances in recent years, catalyzed by breakthroughs in neural radiance fields and 3D Gaussian splatti…