Global-Aware Monocular Semantic Scene Completion with State Space Models

• URL: http://arxiv.org/abs/2503.06569v1
• Date: Sun, 09 Mar 2025 11:55:40 GMT
• Title: Global-Aware Monocular Semantic Scene Completion with State Space Models
• Authors: Shijie Li, Zhongyao Cheng, Rong Li, Shuai Li, Juergen Gall, Xun Xu, Xulei Yang,
• Abstract summary: Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image.<n>Existing methods are often constrained by the local receptive field of Convolutional Networks (CNNs)<n>We introduce GA-MonoSSC, a hybrid architecture for MonoSSC that effectively captures global context in both the 2D image domain and 3D space.
• Score: 25.621011183332094
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image, enabling diverse real-world applications. However, existing methods are often constrained by the local receptive field of Convolutional Neural Networks (CNNs), making it challenging to handle the non-uniform distribution of projected points (Fig. \ref{fig:perspective}) and effectively reconstruct missing information caused by the 3D-to-2D projection. In this work, we introduce GA-MonoSSC, a hybrid architecture for MonoSSC that effectively captures global context in both the 2D image domain and 3D space. Specifically, we propose a Dual-Head Multi-Modality Encoder, which leverages a Transformer architecture to capture spatial relationships across all features in the 2D image domain, enabling more comprehensive 2D feature extraction. Additionally, we introduce the Frustum Mamba Decoder, built on the State Space Model (SSM), to efficiently capture long-range dependencies in 3D space. Furthermore, we propose a frustum reordering strategy within the Frustum Mamba Decoder to mitigate feature discontinuities in the reordered voxel sequence, ensuring better alignment with the scan mechanism of the State Space Model (SSM) for improved 3D representation learning. We conduct extensive experiments on the widely used Occ-ScanNet and NYUv2 datasets, demonstrating that our proposed method achieves state-of-the-art performance, validating its effectiveness. The code will be released upon acceptance.

Related papers

• econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians [56.85804719947]
  We propose econSG for open-vocabulary semantic segmentation with 3DGS. 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)
• UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection [64.65405058535262]
  Recent advances in LiDAR 3D detection have demonstrated the effectiveness of Transformer-based frameworks in capturing the global dependencies from point cloud spaces. Due to the considerable number of 3D voxels and quadratic complexity of Transformers, multiple sequences are grouped before feeding to Transformers, leading to a limited receptive field. Inspired by the impressive performance of State Space Models (SSM) achieved in the field of 2D vision tasks, we propose a novel Unified Mamba (UniMamba) Specifically, a UniMamba block is designed which mainly consists of locality modeling, Z-order serialization and local-global sequential aggregator.
  arXiv  Detail & Related papers  (2025-03-15T06:22:31Z)
• CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction [25.468907201804093]
  Large Reconstruction Models (LRMs) have shown great promise in leveraging multi-view images generated by 2D diffusion models to extract 3D content. However, 2D diffusion models often struggle to produce dense images with strong multi-view consistency. We present CDI3D, a feed-forward framework designed for efficient, high-quality image-to-3D generation with view.
  arXiv  Detail & Related papers  (2025-03-11T03:08:43Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• Semantic Scene Completion with Multi-Feature Data Balancing Network [5.3431413737671525]
  We propose a dual-head model for RGB and depth data (F-TSDF) inputs.<n>Our hybrid encoder-decoder architecture with identity transformation in a pre-activation residual module effectively manages diverse signals within F-TSDF.<n>We evaluate RGB feature fusion strategies and use a combined loss function cross entropy for 2D RGB features and weighted cross-entropy for 3D SSC predictions.
  arXiv  Detail & Related papers  (2024-12-02T12:12:21Z)
• ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction [62.599588577671796]
  We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as robotics or mixed reality.
  arXiv  Detail & Related papers  (2023-11-29T20:30:18Z)
• NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space [77.6067460464962]
  Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. We identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Imbalance in the 3D convolution across different depth levels. We devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2
  arXiv  Detail & Related papers  (2023-09-26T02:09:52Z)
• Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion [0.0]
  We propose a new 2D-based model dubbed Slice SHift UNet which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three planes of a volume. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ axis (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets.
  arXiv  Detail & Related papers  (2023-07-24T14:53:23Z)
• Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training [65.75399500494343]
  Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for 2D and 3D computer vision. We propose Joint-MAE, a 2D-3D joint MAE framework for self-supervised 3D point cloud pre-training.
  arXiv  Detail & Related papers  (2023-02-27T17:56:18Z)

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.