Skip to content

PaperCodex

Subscribe

3D Reconstruction

Depth-supervised NeRF: Achieve High-Quality 3D Reconstruction from Fewer Views and Faster Training—Using Only “Free” Depth from Standard Photogrammetry Pipelines 774

Neural Radiance Fields (NeRF) have revolutionized photorealistic 3D scene reconstruction—but they come with well-known limitations. One major pain point: when…

01/09/20263D Reconstruction, Geometric Deep Learning, Neural Rendering
SLAM3R: Real-Time Dense 3D Reconstruction from Monocular Video—No Camera Calibration Needed

SLAM3R: Real-Time Dense 3D Reconstruction from Monocular Video—No Camera Calibration Needed 1045

Introducing SLAM3R—a cutting-edge, end-to-end system that reconstructs high-quality, dense 3D scenes in real time using only a monocular RGB video…

12/22/20253D Reconstruction, Monocular SLAM, Neural Scene Representation
3DGUT: Real-Time 3D Reconstruction That Handles Distorted Cameras and Reflections Without Sacrificing Speed

3DGUT: Real-Time 3D Reconstruction That Handles Distorted Cameras and Reflections Without Sacrificing Speed 1743

3D Gaussian Splatting (3DGS) revolutionized real-time 3D scene reconstruction by delivering photorealistic quality at high frame rates on consumer GPUs.…

12/22/20253D Reconstruction, Neural Rendering, Real-time Rendering
VGGT: One Model to Reconstruct 3D Scenes Instantly—No Post-Processing Required

VGGT: One Model to Reconstruct 3D Scenes Instantly—No Post-Processing Required 11917

Reconstructing accurate 3D geometry from 2D images has long been a fragmented, multi-step process—requiring separate models for camera pose estimation,…

12/19/20253D Reconstruction, Camera Pose Estimation, Multi-view Geometry
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex