Saved in:
Bibliographic Details
Main Authors: Chen, Xun, Deng, Tianchen, Wang, Rui, Wang, Fangjinhua, Ma, Junyi, Shen, Hongming, Wang, Hesheng, Wang, Danwei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16911
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910226140102656
author Chen, Xun
Deng, Tianchen
Wang, Rui
Wang, Fangjinhua
Ma, Junyi
Shen, Hongming
Wang, Hesheng
Wang, Danwei
author_facet Chen, Xun
Deng, Tianchen
Wang, Rui
Wang, Fangjinhua
Ma, Junyi
Shen, Hongming
Wang, Hesheng
Wang, Danwei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16911
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
Chen, Xun
Deng, Tianchen
Wang, Rui
Wang, Fangjinhua
Ma, Junyi
Shen, Hongming
Wang, Hesheng
Wang, Danwei
Computer Vision and Pattern Recognition
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.
title VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.16911