Memorization in 3D Shape Generation: An Empirical Study

• URL: http://arxiv.org/abs/2512.23628v1
• Date: Mon, 29 Dec 2025 17:39:21 GMT
• Title: Memorization in 3D Shape Generation: An Empirical Study
• Authors: Shu Pu, Boya Zeng, Kaichen Zhou, Mengyu Wang, Zhuang Liu,
• Abstract summary: Generative models are increasingly used in 3D vision to synthesize novel shapes.<n>It remains unclear whether their generation relies on memorizing training shapes.<n>Our framework and analysis provide an empirical understanding of memorization in 3D generative models.
• Score: 12.509533403036798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent training data leakage and improve the diversity of generated results. In this paper, we design an evaluation framework to quantify memorization in 3D generative models and study the influence of different data and modeling designs on memorization. We first apply our framework to quantify memorization in existing methods. Next, through controlled experiments with a latent vector-set (Vecset) diffusion model, we find that, on the data side, memorization depends on data modality, and increases with data diversity and finer-grained conditioning; on the modeling side, it peaks at a moderate guidance scale and can be mitigated by longer Vecsets and simple rotation augmentation. Together, our framework and analysis provide an empirical understanding of memorization in 3D generative models and suggest simple yet effective strategies to reduce it without degrading generation quality. Our code is available at https://github.com/zlab-princeton/3d_mem.

Related papers

• Beyond Frequency: The Role of Redundancy in Large Language Model Memorization [13.044826650528192]
  Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters.<n>We show that frequency increases minimally impact memorized samples while substantially affecting non-memorized samples.<n>Our findings suggest potential redundancy-guided approaches for data preprocessing, thereby reducing privacy risks and mitigating bias to ensure fairness in model deployments.
  arXiv  Detail & Related papers  (2025-06-14T03:02:42Z)
• Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models [31.92526915009259]
  Diffusion models are known for their tremendous ability to generate high-quality samples.<n>Recent methods for memory mitigation have primarily addressed the issue within the context of the text modality.<n>We propose a novel method for diffusion models from the perspective of visual modality, which is more generic and fundamental for mitigating memorization.
  arXiv  Detail & Related papers  (2025-02-13T15:56:44Z)
• A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [65.33043028101471]
  We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision.<n>Most existing 3D generative models rely on full 3D supervision, which is impractical due to the scarcity of large-scale 3D datasets.
  arXiv  Detail & Related papers  (2024-12-01T00:29:57Z)
• A Geometric Framework for Understanding Memorization in Generative Models [11.263296715798374]
  Recent work has shown that deep generative models can be capable of memorizing and reproducing training datapoints when deployed.<n>These findings call into question the usability of generative models, especially in light of the legal and privacy risks brought about by memorization.<n>We propose the manifold memorization hypothesis (MMH), a geometric framework which leverages the manifold hypothesis into a clear language in which to reason about memorization.
  arXiv  Detail & Related papers  (2024-10-31T18:09:01Z)
• Causal Estimation of Memorisation Profiles [58.20086589761273]
  Understanding memorisation in language models has practical and societal implications. Memorisation is the causal effect of training with an instance on the model's ability to predict that instance. This paper proposes a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics.
  arXiv  Detail & Related papers  (2024-06-06T17:59:09Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures [2.167843405313757]
  3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. Many generative learning algorithms require correspondence between each point when comparing the predicted shape and the target shape. We propose an architecture able to cope with different parameterizations, even during the training phase.
  arXiv  Detail & Related papers  (2023-06-27T19:27:15Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• Semi-Supervised Adversarial Recognition of Refined Window Structures for Inverse Procedural Fa\c{c}ade Modeling [17.62526990262815]
  This paper proposes a semi-supervised adversarial recognition strategy embedded in inverse procedural modeling. A simple procedural engine is built inside an existing 3D modeling software, producing fine-grained window geometries. Experiments using publicly available faccade image datasets reveal that the proposed training strategy can obtain about 10% improvement in classification accuracy.
  arXiv  Detail & Related papers  (2022-01-22T06:34:48Z)
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction [61.62191904755521]
  3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. Existing deep learning based methods only focus on the basic cases of skill sequences. We propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences.
  arXiv  Detail & Related papers  (2021-07-31T16:06:50Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.