Hengye Lyu's starred repositories
Depth-Anything-V2
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Depth-Anything
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
segment-anything-edge-detection
Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).
Semantic-Segment-Anything
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
feature-3dgs
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
gaussian_surfels
Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".
dn-splatter
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
nr_in_a_room
Code for "Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objects", ACM ToG
manhattan_sdf
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
IntrinsicImageDiffusion
Intrinsic Image Diffusion for Single-view Material Estimation
awesome-neural-rendering
Resources of Neural Rendering
learning_research
本人的科研经验
2d-gaussian-splatting
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
oneformer3d
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation
L1Flattening
An L1 Image Transform for Edge-Preserving Smoothing and Scene-Level Intrinsic Decomposition
awesome-intrinsic-image-video-decomposition
A collection of intrinsic image/video decomposition based on traditional methods and deep learning methods
S-Aware-network
[AAAI23] Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning, https://arxiv.org/abs/2211.14751
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.