2024.10.09 - #10 - MonST3R, Depth Pro, EVER, KISS-Matcher, Nano-PGO, ST-P3

[changh95]

Academic papers

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

• https://monst3r-project.github.io/page1.html

Screen.Recording.2024-10-09.at.8.50.03.PM.mov

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

• https://github.com/apple/ml-depth-pro

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

• https://arxiv.org/pdf/2410.01804
• 30FPS @ 720p, RTX 4090
• Ray-traces constant-density ellipsoids
• Better than 3DGS

KISS-Matcher: Fast and Robust Point Cloud Registration Revisited

• https://arxiv.org/abs/2409.15615

Diffusion Models in 3D Vision: A Survey

• https://arxiv.org/pdf/2410.04738v1

Nano-PGO

https://youtu.be/tEdIfHYY3uQ?si=xD3nzmGcyKHfi40f

[rubidiumchain]

Paper

ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning