More Works from Our Lab

Paper Title 1

Brief description of the work and its main contribution.

Conference/Journal 2024
Paper Title 2

Brief description of the work and its main contribution.

Conference/Journal 2023
Paper Title 3

Brief description of the work and its main contribution.

Conference/Journal 2023

PointMAC: Meta-learned Adaptation for Robust Test-time Point Cloud Completion

NeurIPS 2025

Linlian Jiang1, Rui Ma2,4, Li Gu1, Ziqiang Wang1, Xinxin Zuo1*, Yang Wang1,3*
1Concordia University 2Jilin University 3Mila - Quebec AI Institute
4Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China
*Corresponding authors
Paper Code arXiv
Overview of PointMAC framework
Existing point cloud completion models operate with fixed inductive biases at inference, often focusing on structurally stable regions (e.g., the fuselage). When such regions are missing, static inference hinders reasoning over other parts (e.g., the tail), resulting in generic completions. Instead, our model applies test-time adaptation using self-supervised signals, enabling dynamic attention to visible cues and producing sample-specific completions that better match the ground truth.

Abstract

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during training, limiting their ability to adapt to novel structural patterns and sensor-induced distortions at test time. To address this limitation, we propose PointMAC, a meta-learned framework for robust test-time adaptation in point cloud completion. It enables sample-specific refinement without requiring additional supervision. Our method optimizes the completion model under two self-supervised auxiliary objectives that simulate structural and sensor-level incompleteness. A meta-auxiliary learning strategy based on Model-Agnostic Meta-Learning (MAML) ensures that adaptation driven by auxiliary objectives is consistently aligned with the primary completion task. During inference, we adapt the shared encoder on-the-fly by optimizing auxiliary losses, with the decoder kept fixed. To further stabilize adaptation, we introduce Adaptive λ-Calibration, a meta-learned mechanism for balancing gradients between primary and auxiliary objectives. Extensive experiments on synthetic, simulated, and real-world datasets demonstrate that PointMAC achieves state-of-the-art results by refining each sample individually to produce high-quality completions. To the best of our knowledge, this is the first work to apply meta-auxiliary test-time adaptation to point cloud completion.

Method

Overview of PointMAC method
Overview of our test-time adaptation method. PointMAC formulates point cloud completion as the primary task and introduces Bi-Aux Units to provide self-supervised signals for test-time adaptation. The encoder 𝓔sh is shared between primary and auxiliary branches. In the meta-learned test-time training phase (a), sample-specific parameters are updated in the inner adaptation using auxiliary losses, while shared parameters are optimized in the outer alignment via the primary completion loss. In the sample-specific TTA phase (b), adaptation proceeds in three steps: (i) the meta-learned model produces initial completions; (ii) the shared encoder 𝓔sh is updated via self-supervised losses from Bi-Aux Units; (iii) sample-specific completions are generated, adapted to the unique structure and noise of each input.

Results

results
Visualization results on the PCN and ShapeNet datasets. Our method preserves fine-grained structures such as the complex geometry of boats and lamps, plane propellers and tails, and chair back slats, demonstrating strong completion quality and generalization across diverse categories.
more results
Visualization of the ablation study on different components of our framework. While jointly training with Bi-Aux Units effectively improves the overall completion quality, it tends to produce generic completion (e.g., a straight lamp arm) that may overlook sample-specific completion (e.g., a circular ring). In contrast, our test-time adaptation strategy personalizes each input by refining the model’s internal representation based on its unique geometry or noise pattern, moving beyond global statistical priors. This leads to more detailed and structurally faithful completions. As a result, the model is better able to preserve subtle, sample-specific structural cues that are often lost under static inference.

BibTeX

@article{jiang2025pointmac,
  title={PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion},
  author={Jiang, Linlian and Ma, Rui and Gu, Li and Wang, Ziqiang and Zuo, Xinxin and Wang, Yang},
  journal={arXiv preprint arXiv:2510.10365},
  year={2025}
}