Visual Geometry Grounded Transformer

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing $O(1)$ frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.

Visual Geometry Foundation Models (VGFMs) demonstrate remarkable zero-shot capabilities in local reconstruction. However, deploying them for kilometer-level Simultaneous Localization and Mapping (SLAM) remains challenging. In such scenarios, current approaches mainly rely on linear transforms (e.g., Sim3 and SL4) for sub-map alignment, while we argue that a single linear transform is fundamentally insufficient to model the complex, non-linear geometric distortions inherent in VGFM outputs. Forcing such rigid alignment leads to the rapid accumulation of uncorrected residuals, eventually resulting in significant trajectory drift and map divergence. To address these limitations, we present CAL2M (Calibration-free Assistant-eye based Large-scale Localization and Mapping), a plug-and-play framework compatible with arbitrary VGFMs. Distinct from traditional systems, CAL2M introduces an "assistant eye" solely to leverage the prior of constant physical spacing, effectively eliminating scale ambiguity without any temporal or spatial pre-calibration. Furthermore, leveraging the assumption of accurate feature matching, we propose an epipolar-guided intrinsic and pose correction model. Supported by an online intrinsic search module, it can effectively rectify rotation and translation errors caused by inaccurate intrinsics through fundamental matrix decomposition. Finally, to ensure accurate mapping, we introduce a globally consistent mapping strategy based on anchor propagation. By constructing and fusing anchors across the trajectory, we establish a direct local-to-global mapping relationship. This enables the application of nonlinear transformations to elastically align sub-maps, effectively eliminating geometric misalignments and ensuring a globally consistent reconstruction. The source code of CAL2M will be publicly available at https://github.com/IRMVLab/CALM.

Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a geometry-based reward model that leverages pretrained geometric foundation models to evaluate multi-view consistency through cross-frame reprojection error. Unlike previous geometric metrics that measure inconsistency in pixel space, where pixel intensity may introduce additional noise, our approach conducts error computation in a pointwise fashion, yielding a more physically grounded and robust error metric. Furthermore, we introduce a geometry-aware sampling strategy that filters out low-texture and non-semantic regions, focusing evaluation on geometrically meaningful areas with reliable correspondences to improve robustness. We apply this reward model to align video diffusion models through two complementary pathways: post-training of a bidirectional model via SFT or Reinforcement Learning and inference-time optimization of a Causal Video Model (e.g., Streaming video generator) via test-time scaling with our reward as a path verifier. Experimental results validate the effectiveness of our design, demonstrating that our geometry-based reward provides superior robustness compared to other variants. By enabling efficient inference-time scaling, our method offers a practical solution for enhancing open-source video models without requiring extensive computational resources for retraining.

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer from geometric distortions and limited camera controllability. To overcome these challenges, we introduce GeoNVS, a geometry-grounded novel-view synthesizer that enhances both geometric fidelity and camera controllability through explicit 3D geometric guidance. Our key innovation is the Gaussian Splat Feature Adapter (GS-Adapter), which lifts input-view diffusion features into 3D Gaussian representations, renders geometry-constrained novel-view features, and adaptively fuses them with diffusion features to correct geometrically inconsistent representations. Unlike prior methods that inject geometry at the input level, GS-Adapter operates in feature space, avoiding view-dependent color noise that degrades structural consistency. Its plug-and-play design enables zero-shot compatibility with diverse feed-forward geometry models without additional training, and can be adapted to other video diffusion backbones. Experiments across 9 scenes and 18 settings demonstrate state-of-the-art performance, achieving 11.3% and 14.9% improvements over SEVA and CameraCtrl, with up to 2x reduction in translation error and 7x in Chamfer Distance.

Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene. We find that prior (absolute or relative) encoding schemes for multi-view attention do not meet these desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays and computes query-frame projective coordinates to ensure SE(3) invariance. To adapt to scene geometry, RayRoPE predicts (without direct supervision) a per-token depth to obtain its position along the corresponding ray, while also modeling uncertainty and analytically computing the expected positional encoding. We validate our method on the tasks of novel-view synthesis, stereo depth estimation, and feed-forward 3DGS reconstruction. While remaining efficient, RayRoPE consistently improves over alternate position encoding schemes (e.g., 24% relative improvement on LPIPS in RE10K).

While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshes with complex geometries remains a significant challenge. Existing efficient architectures often employ feature dimensionality reduction strategies, which inadvertently induces Geometric Aliasing, resulting in the loss of critical physical boundary information. To address this, we propose the Physics-Geometry Operator Transformer (PGOT), designed to reconstruct physical feature learning through explicit geometry awareness. Specifically, we propose Spectrum-Preserving Geometric Attention (SpecGeo-Attention). Utilizing a ``physics slicing-geometry injection" mechanism, this module incorporates multi-scale geometric encodings to explicitly preserve multi-scale geometric features while maintaining linear computational complexity $O(N)$. Furthermore, PGOT dynamically routes computations to low-order linear paths for smooth regions and high-order non-linear paths for shock waves and discontinuities based on spatial coordinates, enabling spatially adaptive and high-precision physical field modeling. PGOT achieves consistent state-of-the-art performance across four standard benchmarks and excels in large-scale industrial tasks including airfoil and car designs.

Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descriptor, we jointly leverage the 3D tokens and intermediate 2D tokens produced by VGGT. Based on their distinct characteristics, we design dedicated aggregation modules for 2D and 3D features, allowing our descriptor to capture fine-grained texture cues while also reasoning across viewpoints. To further enhance generalization, we incorporate both single- and multi-frame aggregation schemes, along with a variable-length sequence retrieval strategy. Our experiments show that UniPR-3D sets a new state of the art, outperforming both single- and multi-view baselines and highlighting the effectiveness of geometry-grounded tokens for VPR. Our code and models will be made publicly available on Github https://github.com/dtc111111/UniPR-3D.

Geometry-grounded vision models, such as VGGT, have emerged as robust visual encoders, providing essential geometric priors for robotic manipulation. However, the high computational cost of these models often leads to slow inference, limiting their practical applications in real-world robotics. This paper introduces eVGGT, a lightweight geometry-aware vision encoder distilled from the high-performing VGGT. Our findings demonstrate two primary advantages: i) integrating eVGGT into imitation learning frameworks (including ACT and Diffusion Policy) yields up to a 6.3% improvement in success rate over standard 2D encoders across bimanual and single-arm tasks in both simulation and real-world settings with variable viewpoints; ii) eVGGT achieves a nearly 5 times speedup and a 63% reduction in memory usage compared to state-of-the-art geometry-aware encoders while maintaining comparable task performance. These results suggest that eVGGT substantially alleviates the performance-latency bottleneck that has limited geometry-aware visuomotor policies in real-world deployment.