Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
cs.CV, cs.AI, cs.GR
Submitted: 2026-04-15
Updated: 2026-10-10
Terminology
Sources
- VGGT: Visual Geometry Grounded Transformer
- Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
- The Replica Dataset: A Digital Replica of Indoor Spaces
- MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
- Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
- Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
- Volume Rendering Digest (for NeRF)
- SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
- MeshLRM: Large Reconstruction Model for High-Quality Meshes
- AGG: Amortized Generative 3D Gaussians for Single Image to 3D
- TripoSR: Fast 3D Object Reconstruction from a Single Image
- CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image
- Depth Anything 3: Recovering the Visual Space from Any Views
- MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
- 3D Reconstruction with Spatial Memory
- PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence
- Streaming 4D Visual Geometry Transformer
- WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
- iLRM: An Iterative Large 3D Reconstruction Model
- G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
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