InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views
cs.CV
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: 21 pages. Project page: https://zju3dv.github.io/InfiniSplat2/
Project page: https://zju3dv.github.io/InfiniSplat2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- C3G: Learning Compact 3D Representations with 2K Gaussians
- VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
- VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
- QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction
- Depth Anything 3: Recovering the Visual Space from Any Views
- WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
- TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
- tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
- InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
- VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
- Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
- ReSplat: Learning Recurrent Gaussian Splatting
- Stereo Magnification: Learning View Synthesis using Multiplane Images
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models