UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition

• URL: http://arxiv.org/abs/2605.07356v1
• Date: Fri, 08 May 2026 07:09:08 GMT
• Title: UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition
• Abstract summary: We propose a unified framework for 2D and 3D semantic segmentation.<n>We combine a SAM-based vision encoder with a SPTNet-based geometric encoder to extract complementary semantic and geometric representations.<n>A lightweight attention-based fusion module aggregates the shared features into a consistent cross-modal representation.
• Score: 9.578297917595377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distortion in image observations complicate cross-modal alignment and hinder stable fusion. Inspired by the fact that 2D images captured by cameras are representations of the 3D world, we recognize that the features learned from 2D and 3D segmentation share some common semantics, while other aspects remain modality-specific. This insight motivates a unified multimodal framework for joint 2D-3D semantic segmentation. We combine a SAM-based vision encoder with a SPTNet-based geometric encoder to extract complementary semantic and geometric representations. The resulting features from both modalities are explicitly decomposed into shared and private subspaces, where the shared components summarize semantic factors common to both domains, and the private components preserve properties that are unique to each modality. A lightweight attention-based fusion module aggregates the shared features into a consistent cross-modal representation, and a regularized training objective ensures both semantic alignment and subspace independence. Experiments on the SemanticKITTI and nuScenes benchmarks demonstrate consistent improvements in segmentation accuracy over representative multimodal baselines, accompanied by competitive computational efficiency. Cross-domain evaluation on nuScenes USA-Singapore shows stable performance under distribution shifts, demonstrating strong generalization. The implementation code is publicly available at: https://github.com/shuaizhang69/UniD-Shift.

Related papers

• USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes [57.4583999658488]
  Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations.<n>Existing methods treat dynamic reconstruction and instance-level perception as separate tasks.<n>We propose USR-Drive, a unified conditional generative framework that recovers dense dynamic geometry and instance-level object layouts within a shared scene representation.
  arXiv  Detail & Related papers  (2026-08-19T15:29:06Z)
• Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement [13.986963122264633]
  We propose a novel framework that produces consistent 2D instance masks to guide the optimization of 3D Gaussian Splatting (3DGS) feature fields.<n>By transforming viewpoint-specific segments into coherent 3D primitives, our approach enables stable 3D instance segmentation and effective downstream editing tasks.
  arXiv  Detail & Related papers  (2026-07-02T05:00:38Z)
• Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression Segmentation [91.2768117730855]
  Generalised 3D Referring Expression (3D-GRES) localizes objects in 3D scenes based on natural language, even when descriptions match multiple or zero targets.<n>Existing methods rely solely on sparse point clouds, lacking rich visual semantics for fine-grained descriptions.<n>We propose HCF-RES, a multi-modal framework with two key innovations.
  arXiv  Detail & Related papers  (2026-03-06T13:09:29Z)
• Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion [73.11061598576798]
  Camera-based occupancy prediction is a mainstream approach for 3D perception in autonomous driving.<n>textbfCIGOcc is a two-stage occupancy prediction framework based on multi-level representation fusion.<n>textbfCIGOcc extracts segmentation, graphics, and depth features from an input image and introduces a deformable multi-level fusion mechanism.
  arXiv  Detail & Related papers  (2025-10-15T06:37:33Z)
• Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge [45.19482892758984]
  Affordance segmentation aims to parse 3D objects into functionally distinct parts, bridging recognition and interaction for applications in robotic manipulation, embodied AI, and AR.<n>We introduce Cross-Modal Affinity Transfer (CMAT), a pre-training strategy that aligns a 3D encoder with lifted 2D semantics and jointly optimize reconstruction, affinity, and diversity to yield semantically organized representations.<n>We further design the Cross-modal Affordance Transformer (CAST), which integrates multi-modal prompts with CMAT-pretrained features to generate precise, prompt-aware segmentation maps.
  arXiv  Detail & Related papers  (2025-10-09T15:01:26Z)
• econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians [56.85804719947]
  We propose econSG for open-vocabulary semantic segmentation with 3DGS.<n>Our econSG shows state-of-the-art performance on four benchmark datasets compared to the existing methods.
  arXiv  Detail & Related papers  (2025-04-08T13:12:31Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving [15.36416000750147]
  We propose a multi-modal 3D semantic segmentation model (MSeg3D) with joint intra-modal feature extraction and inter-modal feature fusion. MSeg3D still shows robustness and improves the LiDAR-only baseline.
  arXiv  Detail & Related papers  (2023-03-15T13:13:03Z)
• Similarity-Aware Fusion Network for 3D Semantic Segmentation [87.51314162700315]
  We propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. We employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds. We show that SAFNet significantly outperforms existing state-of-the-art fusion-based approaches across various data integrity.
  arXiv  Detail & Related papers  (2021-07-04T09:28:18Z)

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.