GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer

• URL: http://arxiv.org/abs/2605.24243v1
• Date: Fri, 22 May 2026 21:42:05 GMT
• Title: GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer
• Abstract summary: In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures.<n>We introduce GIBLy, a lightweight inductive geometric bias layer that integrates priors into 3D segmentation pipelines.<n>We validate our approach across multiple 3D semantic segmentation benchmarks, demonstrating consistent performance gains.
• Score: 41.99844472131922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necessitating large models and more training data which in turn increases cost and can limit generalization. We introduce GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into 3D segmentation pipelines. GIBLy enhances existing architectures -- whether MLP-based, convolution-based, or transformer-based -- by providing features aligned with simple geometric shapes (and thus human-interpretable) that improve segmentation performance with minimal computational overhead. We validate our approach across multiple 3D semantic segmentation benchmarks, demonstrating consistent performance gains, including up to +11.5% mIoU on TS40K with PTV3, while adding only 58K extra parameters. Our results highlight the benefit of explicitly encoding geometric structure to support accurate and efficient 3D scene understanding, with a lightweight add-on layer

Related papers

• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models [70.61152292499737]
  We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm.<n>Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision.<n>We propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation.
  arXiv  Detail & Related papers  (2026-03-17T12:43:48Z)
• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction [14.225228781008209]
  This paper proposes a novel geometry integration mechanism for 3D scene reconstruction. Our approach incorporates 3D geometry at three levels, i.e. feature learning, feature fusion, and network supervision.
  arXiv  Detail & Related papers  (2024-08-28T08:02:47Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• Depth Completion using Geometry-Aware Embedding [22.333381291860498]
  This paper proposes an efficient method to learn geometry-aware embedding. It encodes the local and global geometric structure information from 3D points, e.g., scene layout, object's sizes and shapes, to guide dense depth estimation.
  arXiv  Detail & Related papers  (2022-03-21T12:06:27Z)

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.