zzg-zzg
Follow
Stars
[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!
Official Code and Dataset for "High-fidelity 3D Human Digitization from Single 2K Resolution Images" (CVPR 2023 Highlight)
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.
[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
CUDA accelerated rasterization of gaussian splatting
Efficient 3D reconstruction and relighting of complex scenes with global illumination effects using Neural Radiance Transfer Fields
Fast and memory-efficient exact attention
[CVPR 2022 Oral] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
High-resolution models for human tasks.
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting
including unet,unet++,attention-unet,r2unet,cenet,segnet ,fcn.
[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
[NeurIPS 2024] Official code for "Splatter a Video: Video Gaussian Representation for Versatile Processing"
[TPAMI'23] Unifying Flow, Stereo and Depth Estimation
A procedural Blender pipeline for photorealistic training image generation
Light Transport Gaussian: Relightable 3D Gaussians Based on Precomputed Radiance Transfer
Estimating pose using ArUCo Markers
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction