VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction

• URL: http://arxiv.org/abs/2605.16911v1
• Date: Sat, 16 May 2026 09:51:04 GMT
• Title: VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
• Abstract summary: VGGT-Occ is a framework that embeds geometric tokens throughout the entire pipeline.<n>We introduce Projection-Aware Deformable Attention (PA-DA) to inject geometry into all attention stages.<n>Features are then integrated through a view-quality semantic gate for cross-view consistency.
• Score: 37.542568613707296
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation remain geometry-agnostic, ignoring essential physical constraints. We propose VGGT-Occ, a framework that embeds geometric tokens throughout the entire pipeline. We introduce Projection-Aware Deformable Attention (PA-DA) to inject geometry into all attention stages. PA-DA projects 3D offsets back to image planes and leverages the projection Jacobian as an additive bias to suppress unreliable observations. Features are then integrated through a view-quality semantic gate for cross-view consistency. To optimize both efficiency and performance, we employ a sequential coarse-to-fine decoder with gated fusion, where low-resolution features are refined into higher resolutions, allocating computation by information density while substantially reducing decoder cost. Extensive evaluations demonstrate the effectiveness and accuracy of our approach. On SurroundOcc-nuScenes, VGGT-Occ achieves 33.00\% IoU and 21.08\% mIoU ($T{=}1$), and 33.64\% IoU and 21.43\% mIoU with $T{=}2$ inference, outperforming existing methods, with only ${\sim}41$M trainable parameters in the occupancy head. Code will be released publicly.

Related papers

• Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation [76.16065370700488]
  We introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation.<n>We show that Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods.
  arXiv  Detail & Related papers  (2026-07-07T17:59:47Z)
• GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth [12.866152238833104]
  Video depth estimation extends monocular prediction into the temporal domain to ensure coherence.<n>Current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency.<n>We propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency.
  arXiv  Detail & Related papers  (2026-05-11T13:11:54Z)
• 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)
• GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation [57.8059956428009]
  Recent attempts to transfer features from 2D Vision-Language Models to 3D semantic segmentation expose a persistent trade-off.<n>We propose GeoPurify that applies a small Student Affinity Network to 2D VLM-generated 3D point features using geometric priors distilled from a 3D self-supervised teacher model.<n>Benefiting from latent geometric information and the learned affinity network, GeoPurify effectively mitigates the trade-off and achieves superior data efficiency.
  arXiv  Detail & Related papers  (2025-10-02T16:37:56Z)
• DA-Occ: Efficient 3D Voxel Occupancy Prediction via Directional 2D for Geometric Structure Preservation [13.792614780020061]
  Efficient and high-accuracy 3D occupancy prediction is crucial for ensuring the performance of autonomous driving systems.<n>Our method involves slicing 3D voxel features to preserve complete vertical geometric information.<n>This strategy compensates for the loss of height cues in Bird's-Eye View representations, thereby maintaining the integrity of the 3D geometric structure.
  arXiv  Detail & Related papers  (2025-07-31T14:39:31Z)
• ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions [91.55655961014027]
  3D semantic occupancy and flow prediction are fundamental to understanding scene scene.<n>This paper proposes a vision-based framework with three targeted improvements.<n>Our purely convolutional architecture establishes new SOTA performance on multiple benchmarks for both semantic occupancy and joint semantic-flow prediction.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement [8.592248643229675]
  Occupancy prediction plays a pivotal role in autonomous driving (AD) Existing methods often incur high computational costs, which contradicts the real-time demands of AD. We propose a Geometric-Semantic Dual-Branch Network (GSDBN) with a hybrid BEV-Voxel representation.
  arXiv  Detail & Related papers  (2024-07-18T04:46:13Z)
• 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)
• PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction [72.75478398447396]
  We propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively. Considering the distance distribution of LiDAR point clouds, we construct the tri-perspective view in the cylindrical coordinate system. We employ spatial group pooling to maintain structural details during projection and adopt 2D backbones to efficiently process each TPV plane.
  arXiv  Detail & Related papers  (2023-08-31T17:57:17Z)
• OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection [51.153003057515754]
  OPA-3D is a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network. It jointly estimates dense scene depth with depth-bounding box residuals and object bounding boxes. It outperforms state-of-the-art methods on the main Car category.
  arXiv  Detail & Related papers  (2022-11-02T14:19:13Z)

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.