Related papers: Spark3R: Asymmetric Token Reduction Makes Fast Fee…
Recent advances in 3D Gaussian Splatting (3DGS) present two main directions: feed-forward models offer fast inference in sparse-view settings, while per-scene optimization yields high-quality renderings but is computationally expensive. To…
This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of…
Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…
Stylizing 3D scenes instantly while maintaining multi-view consistency and faithfully resembling a style image remains a significant challenge. Current state-of-the-art 3D stylization methods typically involve computationally intensive…
We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows impacts feed-forward 3D reconstruction. Although recent object-centric feed-forward methods deliver robust, high-quality reconstruction,…
Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…
Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…
Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D…
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.…
Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…
In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…
Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…
Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current…
Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from heavy computational costs induced by the massive number…
We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…
Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly…
Reconstructing and tracking dynamic 3D scenes remains a fundamental challenge in computer vision. Existing approaches often decouple geometry from motion: multi-view reconstruction methods assume static scenes, while dynamic tracking…
Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization. MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching…
Visual SLAM is a cornerstone technique in robotics, autonomous driving and extended reality (XR), yet classical systems often struggle with low-texture environments, scale ambiguity, and degraded performance under challenging visual…