Stars
NVIDIA Cosmos-Dreams (fka NVIDIA OmniDreams) is a world model that generates photorealistic video for autonomous-driving simulation in real time.
InstantNuRec: Feed-Forward 3D Gaussian Reconstruction from Driving Logs
[CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction
Masked Depth Modeling for Spatial Perception
An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.
A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…
Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.
[TPAMI 2026] 3D and 4D World Modeling: A Survey
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
COLMAP - Structure-from-Motion and Multi-View Stereo
Effectively Detecting Loop Closures using Point Cloud Density Maps
LSD (LiDAR SLAM & Detection) is an open source perception architecture for autonomous vehicle/robotic