Related papers: LiteVGGT: Boosting Vanilla VGGT via Geometry-aware…

Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, scaling these models to long-sequence image inputs remains a significant challenge due to inference-time inefficiency. In this…

The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass.…

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of…

Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal…

Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single forward pass.…

Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to deliver robust and efficient streaming 3D reconstruction.…

Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…

3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce…

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…

Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong streaming reconstruction, but suffers from unbounded KV cache…

Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…

Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…

The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction without per-scene optimization. However, its billion-parameter scale creates high memory and compute demands, hindering on-device deployment.…

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…

Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these…

We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by…