Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding

• URL: http://arxiv.org/abs/2504.06719v1
• Date: Wed, 09 Apr 2025 09:19:49 GMT
• Title: Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
• Authors: Pedro Hermosilla, Christian Stippel, Leon Sick,
• Abstract summary: This paper proposes a robust evaluation protocol to assess the quality of self-supervised features for 3D scene understanding.<n>We introduce the first self-supervised model that performs similarly to supervised models when only off-the-shelf features are used in a linear probing setup.<n>Our experiments not only demonstrate that our method achieves competitive performance to supervised models, but also surpasses existing self-supervised approaches by a large margin.
• Score: 5.035452169519211
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene understanding, self-supervised methods are typically only used as a weight initialization step for task-specific fine-tuning, limiting their utility for general-purpose feature extraction. This paper addresses this shortcoming by proposing a robust evaluation protocol specifically designed to assess the quality of self-supervised features for 3D scene understanding. Our protocol uses multi-resolution feature sampling of hierarchical models to create rich point-level representations that capture the semantic capabilities of the model and, hence, are suitable for evaluation with linear probing and nearest-neighbor methods. Furthermore, we introduce the first self-supervised model that performs similarly to supervised models when only off-the-shelf features are used in a linear probing setup. In particular, our model is trained natively in 3D with a novel self-supervised approach based on a Masked Scene Modeling objective, which reconstructs deep features of masked patches in a bottom-up manner and is specifically tailored to hierarchical 3D models. Our experiments not only demonstrate that our method achieves competitive performance to supervised models, but also surpasses existing self-supervised approaches by a large margin. The model and training code can be found at our Github repository (https://github.com/phermosilla/msm).

Related papers

• DINeMo: Learning Neural Mesh Models with no 3D Annotations [7.21992608540601]
  Category-level 3D/6D pose estimation is a crucial step towards comprehensive 3D scene understanding. Recent works explored neural mesh models that approach a range of 2D and 3D tasks from an analysis-by-synthesis perspective. We present DINeMo, a novel neural mesh model that is trained with no 3D annotations by leveraging pseudo-correspondence.
  arXiv  Detail & Related papers  (2025-03-26T04:23:53Z)
• A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [65.33043028101471]
  We introduce a diffusion model for Gaussian Splats, SplatDiffusion, to enable generation of three-dimensional structures from single images.<n>Existing methods rely on deterministic, feed-forward predictions, which limit their ability to handle the inherent ambiguity of 3D inference from 2D data.
  arXiv  Detail & Related papers  (2024-12-01T00:29:57Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP [19.66617835750012]
  Training a 3D scene understanding model requires complicated human annotations. vision-language pre-training models (e.g., CLIP) have shown remarkable open-world reasoning properties. We propose directly transferring CLIP's feature space to 3D scene understanding model without any form of supervision.
  arXiv  Detail & Related papers  (2023-03-08T17:30:58Z)
• Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation [66.21121745446345]
  We propose a conditional GNeRF model that integrates specific attribute labels as input, thus amplifying the controllability and disentanglement capabilities of 3D-aware generative models. Our approach builds upon a pre-trained 3D-aware face model, and we introduce a Training as Init and fidelity for Tuning (TRIOT) method to train a conditional normalized flow module. Our experiments substantiate the efficacy of our model, showcasing its ability to generate high-quality edits with enhanced view consistency.
  arXiv  Detail & Related papers  (2022-08-26T10:05:39Z)
• Stereo Neural Vernier Caliper [57.187088191829886]
  We propose a new object-centric framework for learning-based stereo 3D object detection. We tackle a problem of how to predict a refined update given an initial 3D cuboid guess. Our approach achieves state-of-the-art performance on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-03-21T14:36:07Z)
• Contrastive Neighborhood Alignment [81.65103777329874]
  We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one.
  arXiv  Detail & Related papers  (2022-01-06T04:58:31Z)
• SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection [9.924083358178239]
  We propose two variants of self-attention for contextual modeling in 3D object detection. We first incorporate the pairwise self-attention mechanism into the current state-of-the-art BEV, voxel and point-based detectors. Next, we propose a self-attention variant that samples a subset of the most representative features by learning deformations over randomly sampled locations.
  arXiv  Detail & Related papers  (2021-01-07T18:30:32Z)
• PerMO: Perceiving More at Once from a Single Image for Autonomous Driving [76.35684439949094]
  We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image. Our approach combines the strengths of deep learning and the elegance of traditional techniques. We have integrated these algorithms with an autonomous driving system.
  arXiv  Detail & Related papers  (2020-07-16T05:02:45Z)
• PolyGen: An Autoregressive Generative Model of 3D Meshes [22.860421649320287]
  We present an approach which models the mesh directly using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images. We show that the model is capable of producing high-quality, usable meshes, and establish log-likelihood benchmarks for the mesh-modelling task.
  arXiv  Detail & Related papers  (2020-02-23T17:16:34Z)

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.