Papers › Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

4 Oct 2023arXiv:2310.03059archive 2025-07-28

Yiwen Tang, Ray Zhang, Zoey Guo, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li

The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning (PEFT) techniques are proposed for language and 2D image pre-trained models. However, the specialized PEFT method for 3D pre-trained models is still under-explored. To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks, which consist of a Point-prior Prompt and a Geometry-aware Adapter. The Point-prior Prompt adopts a set of learnable prompt tokens, for which we propose to construct a memory bank with domain-specific knowledge, and utilize a parameter-free attention to enhance the prompt tokens. The Geometry-aware Adapter aims to aggregate point cloud features within spatial neighborhoods to capture fine-grained geometric information through local interactions. Extensive experiments indicate that our Point-PEFT can achieve better performance than the full fine-tuning on various downstream tasks, while using only 5% of the trainable parameters, demonstrating the efficiency and effectiveness of our approach. Code is released at https://github.com/Ivan-Tang-3D/Point-PEFT.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

EvenJoker/Point-PEFT officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding (arXiv:2404.07989; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
even-jk/peft-3d officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding (arXiv:2404.07989; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
ivan-tang-3d/peft-3d officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
ivan-tang-3d/point-peft officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ivan-tang-3d/any2point mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ivan-tang-3d/viewrefer3d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ziyuguo99/viewrefer3d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding (arXiv:2404.07989; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

parameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adapter

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections