Lists (8)
Awesome Lists
Digital Twins
GS / NeRF
Multimodal/Foundation/OpenVocab
Papers related to vision-language, multi-modal, multi-sensor, foundation models and open vocabulary modelsMVS / SfM / SLAM / Depth / Pose
Papers related to SfM, MVS, SLAM, Depth, Matching, and camera pose estimation methods.Recognition/ Detection/ Tracking
Papers related to recognition, detection, tracking and pre-training methods.Scene Reconstruction/ Understand
Papers related to scene reconstruction, understanding, and simulation.Tools / Datasets
Papers and Projects related to useful tools and datasets.Stars
A comprehensive list of Implicit Representations, NeRF and 3D Gaussian Splatting papers relating to SLAM/Robotics domain, including papers, videos, codes, and related websites
ACE-SLAM: Scene Coordinate Regression for Real-Time SLAM
[CVPR 2025] ZeroMSF: Zero-shot Monocular Scene Flow Estimation in the Wild
Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory
In Pursuit of Pixel Supervision for Visual Pre-training
[NeurIPS 2025] LabelAny3D: Label Any Object 3D in the Wild
🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.
An invigorating blend of 3D geometry tools in Python.
"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.
Lang2Motion: Bridging Language and Motion through Joint Embedding Spaces
Any4D: Unified Feed-Forward Metric 4D Reconstruction
Sharp Monocular View Synthesis in Less Than a Second
[NeurIPS 25] TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
[SIGGRAPHASIA2025] InfiniHuman: Infinite 3D Human Creation with Precise Control
Optimizing Monocular Depth Estimation with TensorRT: Model Conversion, Inference Acceleration, and 3D Reconstruction
Official implementation of "Emergent Outlier View Rejection in Visual Geometry Grounded Transformers"
Official implementation of "C3G: Learning Compact 3D Representations with 2K Gaussians"
Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras
FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 Spotlight)
🎤 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
[NeurIPS 2025] Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation