Stars
A curated list of awesome 3D scene generation papers. (arXiv 2505.05474)
A fast structure from motion pipeline written in Pytorch.
[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models
[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
A simple training-free approach adapting DUSt3R for dynamic scenes.
[CVPR 2025 Oral] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
This is a PyTorch implementation of the ECCV2020 paper "DeepSFM: Structure From Motion Via Deep Bundle Adjustment".
<Foundations of Computer Vision> Book
[ICML 2025] Official Implementation for SimDINO/SimDINOv2
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
[CVPR 2025] AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.
SpatialLM: Large Language Model for Spatial Understanding
Stereo4D dataset and processing code
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
A Game of Bundle Adjustment - Learning Efficient Convergence - Accepted to ICCV 2023
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)
PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start exploring your 3D world via text!
[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation