The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

[CVPR23 Highlight] Implementation for Panoptic Lifting

具身智能入门指南

Animation engine for explanatory math videos

[ECCV 2024] GenRC: 3D Indoor Scene Generation from Sparse Image Collections

Official code for "Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction" (CVPR 2023)

Code for the paper: "ODIN: A Single Model for 2D and 3D Segmentation" (CVPR 2024)

Official repository of **CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation, ECCV'24**

Dense Optical Tracking: Connecting the Dots

Official code for "RealFusion: 360° Reconstruction of Any Object from a Single Image" (CVPR 2023)

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

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 2024] MemFlow: Optical Flow Estimation and Prediction with Memory

Official implementation of the paper "Feature Splatting for Better Novel View Synthesis with Low Overlap"

Official implementation of the paper "GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane"(ACM MM2024).

3D Reconstruction with Spatial Memory

This is a list of awesome paper about optical flow and related work.

PyTorch code and models for the DINOv2 self-supervised learning method.

Undistorted Depth Support for ScanNet++

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

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

[ICRA'24] Accurate Prior-centric Monocular Positioning with Offline LiDAR Fusion

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

[ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"

CoTracker is a model for tracking any point (pixel) on a video.