Papers with Code 아카이브

3D Object Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 4
보존된 평가 기록: 14

3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.

Image: Sedaghat et al

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/tangyuan96/minigpt-3d

공식 코드

MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

https://github.com/weiguangzhao/diff-op3d

공식 코드

Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges

https://github.com/xiaogangw/cascaded-point-completion

공식 코드

Cascaded Refinement Network for Point Cloud Completion with Self-supervision

https://github.com/zhimin-c/multiview-mae

공식 코드

Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder

https://github.com/ziyuguo99/point-bind_point-llm

공식 코드

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

https://github.com/AliBahri94/SVWA_TTA

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

https://github.com/CPUFronz/CapsVoxGAN

3D Point Capsule Networks

https://github.com/CorleoneJW/3D-Retrieval-System

A Fast Hybrid Cascade Network for Voxel-based 3D Object Classification

https://github.com/Daniel-Liu-c0deb0t/3D-Neural-Network-Adversarial-Attacks

Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers

https://github.com/Pointcept/GPT4Point

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

https://github.com/WDot/G3DNet

https://github.com/Yui010206/CREMA

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

https://github.com/baaivision/GeoDream

Uni3D: Exploring Unified 3D Representation at Scale

https://github.com/code-implementation1/Code1/tree/main/DDAG

Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges

https://github.com/hamidreza-dastmalchi/3dd-tta

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

https://github.com/hrisi/tree-species-classification

PointMixer: MLP-Mixer for Point Cloud Understanding

https://github.com/ismav/sparseNMF

Block Coordinate Descent for Sparse NMF

https://github.com/krips89/mlh_mvcnn

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

https://github.com/qizekun/ReCon

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

https://github.com/qq456cvb/Point-Transformers

Point Transformer

https://github.com/runpeidong/act

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

https://github.com/rusty1s/pytorch_cluster

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

https://github.com/snehaputul/CrossMoCo

https://github.com/suryanshkumar/online-joint-depthfusion-and-semantic

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

https://github.com/umass-foundation-model/3d-llm

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

https://github.com/yongheng1991/3D-point-capsule-networks

3D Point Capsule Networks

https://github.com/yossilevii100/critical_points2

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

https://github.com/yossilevii100/refocusing

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

https://github.com/zb12138/sph3d

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

https://github.com/zb12138/sph3dR

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

https://github.com/zrrskywalker/point-bind

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.