6 papers
Revisiting 3D Reconstruction Kernels as Low-Pass Filters
Shengjun Zhang, Min Chen, Yibo Wei +2
3D reconstruction is to recover 3D signals from the sampled discrete 2D pixels, with the goal to converge continuous 3D spaces. In this paper, we revisit 3D reconstruction from the…
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Shengjun Zhang, Zhang Zhang, Chensheng Dai +1
Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existi…
ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment
Chong Xia, Shengjun Zhang, Fangfu Liu +3
Perpetual 3D scene generation aims to produce long-range and coherent 3D view sequences, which is applicable for long-term video synthesis and 3D scene reconstruction. Existing met…
Learning Efficient and Generalizable Human Representation with Human Gaussian Model
Yifan Liu, Shengjun Zhang, Chensheng Dai +4
Modeling animatable human avatars from videos is a long-standing and challenging problem. While conventional methods require per-instance optimization, recent feed-forward methods…
Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model
Shengjun Zhang, Jinzhao Li, Xin Fei +2
In this paper, we propose Scene Splatter, a momentum-based paradigm for video diffusion to generate generic scenes from single image. Existing methods, which employ video generatio…
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Shengjun Zhang, Xin Fei, Fangfu Liu +2
3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis performance. While conventional methods require per-scene optimization, more recently several feed-for…