yuqunw Goto Github PK

3d-llm

Preliminary Code for 3D-LLM: Injecting the 3D World into Large Language Models

applied-machine-learning

Simple code implementations of undergrad machine learning concepts

cache

concept-graphs

Official code release for ConceptGraphs

cvpr2021-paper-code-interpretation

cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

denseclip

dinov2

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

edge-detection---canny-detector

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

general_purpose_vision_normals

grounded-segment-anything

Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

inverserenderingofindoorscene

llava-mod

(very slight) modifications to llava to allow inference over precomputed features

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

marigold

Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

monopatch_nerf

monosdf

[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

nerfacc

A General NeRF Acceleration Toolbox in PyTorch.

nerfacc_yuqun

neuralangelo

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

nksr

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

osrt

Independent PyTorch Implementation of Object Scene Representation Transformer

panoptic-lifting

[CVPR23 Highlight] Implementation for Panoptic Lifting

robustmvd

Repository for the Robust Multi-View Depth Benchmark

shell

tech_review

final project tech review

tracking-anything-with-deva

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

videomae

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

website