Lidar Localization and Mapping

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

[3DV'25] 3D Reconstruction with Spatial Memory

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

[ICCV 2025] ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

Code for FastVGGT: Training-Free Acceleration of Visual Geometry Transformer

[IROS 2025] ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model

[NeurIPS 2025] MLLMs Need 3D-Aware Representation Supervision for Scene Understanding

ViPE: Video Pose Engine for Geometric 3D Perception

Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

[ICCV 2025] HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)

Awesome Spatial Intelligence (Personal Use)

X-SAM: From Segment Anything to Any Segmentation

Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Official implement of VGGT-Long

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Code for Streaming 4D Visual Geometry Transformer

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

Cameras as Relative Positional Encoding