Any Resolution Any Geometry: From Multi-View To Multi-Patch
This work addresses the problem of preserving fine local detail while maintaining global consistency in 3D geometry estimation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the challenge of high-resolution joint estimation of surface normals and depth for 3D scene understanding by proposing the Ultra Resolution Geometry Transformer (URGT), which achieves state-of-the-art results on UnrealStereo4K, reducing AbsRel from 0.0582 to 0.0291, RMSE from 2.17 to 1.31, and mean angular error from 23.36 degrees to 18.51 degrees.
Joint estimation of surface normals and depth is essential for holistic 3D scene understanding, yet high-resolution prediction remains difficult due to the trade-off between preserving fine local detail and maintaining global consistency. To address this challenge, we propose the Ultra Resolution Geometry Transformer (URGT), which adapts the Visual Geometry Grounded Transformer (VGGT) into a unified multi-patch transformer for monocular high-resolution depth--normal estimation. A single high-resolution image is partitioned into patches that are augmented with coarse depth and normal priors from pre-trained models, and jointly processed in a single forward pass to predict refined geometric outputs. Global coherence is enforced through cross-patch attention, which enables long-range geometric reasoning and seamless propagation of information across patches within a shared backbone. To further enhance spatial robustness, we introduce a GridMix patch sampling strategy that probabilistically samples grid configurations during training, improving inter-patch consistency and generalization. Our method achieves state-of-the-art results on UnrealStereo4K, jointly improving depth and normal estimation, reducing AbsRel from 0.0582 to 0.0291, RMSE from 2.17 to 1.31, and lowering mean angular error from 23.36 degrees to 18.51 degrees, while producing sharper and more stable geometry. The proposed multi-patch framework also demonstrates strong zero-shot and cross-domain generalization and scales effectively to very high resolutions, offering an efficient and extensible solution for high-quality geometry refinement.