RDGSplat: Render-Dedicated Geometry for Novel View Synthesis
cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
- SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
- Gaussian Set Surface Reconstruction through Per-Gaussian Optimization
- AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
- Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction
- Depth Anything 3: Recovering the Visual Space from Any Views
- POMA-3D: The Point Map Way to 3D Scene Understanding
- OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer
- 2DGS-R: Revisiting the Normal Consistency Regularization in 2D Gaussian Splatting
- AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling
- Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
- HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
- AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
- Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
- AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
- Emergent Extreme-View Geometry in 3D Foundation Models
- $\text{VG}^2$GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
- Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
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