9 papers
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Chongjian Ge, Hanwen Jiang, Tianyu Wang +9
Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera,…
Softmax-GS: Generalized Gaussians Learning When to Blend or Bound
Chen Ziwen, Peng Wang, Hao Tan +2
3D Gaussian Splatting (3D GS) is widely adopted for novel view synthesis due to its high training and rendering efficiency. However, its efficiency relies on the key assumption tha…
Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
Chen Ziwen, Hao Tan, Peng Wang +2
Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 in…
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
Ziqiao Ma, Xuweiyi Chen, Shoubin Yu +10
Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative…
GS4: Generalizable Sparse Splatting Semantic SLAM
Mingqi Jiang, Chanho Kim, Chen Ziwen +1
Traditional SLAM algorithms excel at camera tracking, but typically produce incomplete and low-resolution maps that are not tightly integrated with semantics prediction. Recent wor…
Generating 360° Video is What You Need For a 3D Scene
Zhaoyang Zhang, Yannick Hold-Geoffroy, Miloš Hašan +4
Generating 3D scenes is still a challenging task due to the lack of readily available scene data. Most existing methods only produce partial scenes and provide limited navigational…
MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
Hanwen Jiang, Zexiang Xu, Desai Xie +11
We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes -…
PointRecon: Online Point-based 3D Reconstruction via Ray-based 2D-3D Matching
Chen Ziwen, Zexiang Xu, Li Fuxin
We propose a novel online, point-based 3D reconstruction method from posed monocular RGB videos. Our model maintains a global point cloud representation of the scene, continuously…
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
Chen Ziwen, Hao Tan, Kai Zhang +5
We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360° wide-coverage, scene-level reconstruction. Specifically, it takes in 32 inpu…