running colmap with given camera pose

[CVPR 2024] Official implementation of "SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration"

Accelerating SDF gradient computation in NeuS-like multi-view reconstruction with directional finite difference (DFD) and patch-based sampling.

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

Official implementation of "Bilateral Normal Integration" (BiNI), ECCV 2022.

[CVPR'24, Demo Track Honourable Mention] SuperPrimitive: Scene Reconstruction at a Primitive Level

[3DV 2024] Official repo of "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans"

Webpage of "Root Pose Decomposition"

Official repository for the ICCV 2021 paper: UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model.

Dynamic Surface Function Networks for Clothed Human Bodies

Repositories from THU-3DHuman

Fitting SMPL human body model to depth images in CPU real-time (combining SMPLify, original Kinect; new version of OpenARK avatar)

code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"

The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.

SPAMs: Structured Implicit Parametric Models [CVPR 22]

[CVPR'24] LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)

Fast CPU rendering in Python using the Intel® Embree backend

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

This software (CMVS) takes the output of a structure-from-motion (SfM) software as input, then decomposes the input images into a set of image clusters of managable size. An MVS software can be use…

(ICLR 2024) PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

Official Code For Track Everything Everywhere Fast and Robustly

[arXiv 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

Flexible Feature Engineering & Exploration Library using GPUs and Optuna.

Visualizing the DROID dataset using Rerun

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)