SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.11487 · 2023

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
CGuangyan-BIT/PointGPT canonical 6 of 7
FunctionStatusWhere it lives
farthest_point_sample Ran CGuangyan-BIT/PointGPT/datasets/ModelNetDataset.py
code served (permissive licence) · get_code("f80066a00e7156a2")
get_z_order Ran CGuangyan-BIT/PointGPT/models/z_order.py
code served (permissive licence) · get_code("8211b3ca522ad7c8")
pc_normalize Ran CGuangyan-BIT/PointGPT/datasets/ModelNetDataset.py
code served (permissive licence) · get_code("4783fbece52f500e")
round_to_int_32 Ran CGuangyan-BIT/PointGPT/models/z_order.py
code served (permissive licence) · get_code("936ad378b238e868")
split_by_3 Ran CGuangyan-BIT/PointGPT/models/z_order.py
code served (permissive licence) · get_code("2901d555b5635d05")
square_distance Ran CGuangyan-BIT/PointGPT/segmentation/pointnet_util.py
code served (permissive licence) · get_code("74c3fe06cea2f553")
timeit Not yet run CGuangyan-BIT/PointGPT/segmentation/pointnet_util.py
code served (permissive licence) · get_code("b1227ddb721e2999")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps. Specifically, a point cloud auto-regressive generation task is proposed to pre-train transformer models. Our method partitions the input point cloud into multiple point patches and arranges them in an ordered sequence based on their spatial proximity. Then, an extractor-generator based transformer decoder, with a dual masking strategy, learns latent representations conditioned on the preceding point patches, aiming to predict the next one in an auto-regressive manner. Our scalable approach allows for learning high-capacity models that generalize well, achieving state-of-the-art performance on various downstream tasks. In particular, our approach achieves classification accuracies of 94.9% on the ModelNet40 dataset and 93.4% on the ScanObjectNN dataset, outperforming all other transformer models. Furthermore, our method also attains new state-of-the-art accuracies on all four few-shot learning benchmarks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.11487")
get_code_for_paper("2305.11487")
have("2305.11487")

Connect an agent — have() is free.