UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images

• URL: http://arxiv.org/abs/2603.17519v1
• Date: Wed, 18 Mar 2026 09:26:25 GMT
• Title: UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images
• Abstract summary: We propose UniSem, a unified framework that improves depth accuracy and semantic generalization via two key components.<n>Error-aware Gaussian Dropout (EGD) performs error-guided capacity control by suppressing redundancy-prone Gaussians.<n>Second, we introduce a Mix-training Curriculum (MTC) that blends 2D segmenter-lifted semantics with the model's own emergent 3D semantic priors.
• Score: 10.080087958100552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic-aware 3D reconstruction from sparse, unposed images remains challenging for feed-forward 3D Gaussian Splatting (3DGS). Existing methods often predict an over-complete set of Gaussian primitives under sparse-view supervision, leading to unstable geometry and inferior depth quality. Meanwhile, they rely solely on 2D segmenter features for semantic lifting, which provides weak 3D-level and limited generalizable supervision, resulting in incomplete 3D semantics in novel scenes. To address these issues, we propose UniSem, a unified framework that jointly improves depth accuracy and semantic generalization via two key components. First, Error-aware Gaussian Dropout (EGD) performs error-guided capacity control by suppressing redundancy-prone Gaussians using rendering error cues, producing meaningful, geometrically stable Gaussian representations for improved depth estimation. Second, we introduce a Mix-training Curriculum (MTC) that progressively blends 2D segmenter-lifted semantics with the model's own emergent 3D semantic priors, implemented with object-level prototype alignment to enhance semantic coherence and completeness. Extensive experiments on ScanNet and Replica show that UniSem achieves superior performance in depth prediction and open-vocabulary 3D segmentation across varying numbers of input views. Notably, with 16-view inputs, UniSem reduces depth Rel by 15.2% and improves open-vocabulary segmentation mAcc by 3.7% over strong baselines.

Related papers

• PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting [15.208505879476418]
  Unsupervised point cloud segmentation is critical for embodied artificial intelligence and autonomous driving.<n>This paper proposes PointGS, a simple yet effective pipeline for unsupervised 3D point cloud segmentation.<n> Experiments demonstrate that PointGS outperforms state-of-the-art unsupervised methods.
  arXiv  Detail & Related papers  (2026-05-12T04:44:50Z)
• NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting [41.21645092733966]
  We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features.<n> Experiments show that our method enhances the accuracy of lifted semantics, providing an efficient and effective approach to robust 3D semantic Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-24T10:57:05Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• 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)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning [46.85417907244265]
  We propose an interpretable single-view 3DGS framework, termed 3DisGS, to discover both coarse- and fine-grained 3D semantics.<n>Our model achieves 3D disentanglement while preserving high-quality and rapid reconstruction.
  arXiv  Detail & Related papers  (2025-04-05T14:42:13Z)
• TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views [18.050257821756148]
  TSGaussian is a novel framework that combines semantic constraints with depth priors to avoid geometry degradation in novel view synthesis tasks.<n>Our approach prioritizes computational resources on designated targets while minimizing background allocation.<n>Extensive experiments demonstrate that TSGaussian outperforms state-of-the-art methods on three standard datasets.
  arXiv  Detail & Related papers  (2024-12-13T11:26:38Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding [17.440124130814166]
  Exploiting 3D Gaussian Splatting (3DGS) with Contrastive Language-Image Pre-Training (CLIP) models for open-vocabulary 3D semantic understanding of indoor scenes has emerged as an attractive research focus.<n>We present CLIP-GS, efficiently achieving a coherent semantic understanding of 3D indoor scenes via the proposed Semantic Attribute Compactness (SAC) and 3D Coherent Regularization (3DCR)<n>Our method remarkably suppresses existing state-of-the-art approaches, achieving mIoU improvements of 21.20% and 13.05% on ScanNet and Replica datasets, respectively
  arXiv  Detail & Related papers  (2024-04-22T15:01:32Z)
• Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation [75.44912541912252]
  We propose a three-stage framework named Multi-Initialization Optimization Network (MION) In the first stage, we strategically select different coarse 3D reconstruction candidates which are compatible with the 2D keypoints of input sample. In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism. Finally, a Consistency Estimation Network (CEN) is proposed to find the best result from mutiple candidates by evaluating if the visual evidence in RGB image matches a given 3D reconstruction.
  arXiv  Detail & Related papers  (2021-12-24T02:43:58Z)

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.