English
Related papers

Related papers: HTTM: Head-wise Temporal Token Merging for Faster …

200 papers

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for long sequences, limiting application to large-scale scenes…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Zhijian Shu , Cheng Lin , Tao Xie , Wei Yin , Ben Li , Zhiyuan Pu , Weize Li , Yao Yao , Xun Cao , Xiaoyang Guo , Xiao-Xiao Long

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 You Shen , Zhipeng Zhang , Yansong Qu , Xiawu Zheng , Jiayi Ji , Shengchuan Zhang , Liujuan Cao

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Tianrun Chen , Yuanqi Hu , Yidong Han , Hanjie Xu , Deyi Ji , Qi Zhu , Chunan Yu , Xin Zhang , Cheng Chen , Chaotao Ding , Ying Zang , Xuanfu Li , Jin Ma , Lanyun Zhu

Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Jeongseok Hyun , Sukjun Hwang , Su Ho Han , Taeoh Kim , Inwoong Lee , Dongyoon Wee , Joon-Young Lee , Seon Joo Kim , Minho Shim

Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Jung Hwan Heo , Seyedarmin Azizi , Arash Fayyazi , Massoud Pedram

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Zipeng Wang , Dan Xu

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.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 David Huang , Guile Wu , Chengjie Huang , Bingbing Liu , Dongfeng Bai

We present a fast, spatio-temporal scene understanding framework based on Visual Geometry Grounded Transformer (VGGT). The proposed pipeline is designed to enable efficient, close to real-time performance, supporting applications including…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Gergely Dinya , Péter Halász , András Lőrincz , Kristóf Karacs , Anna Gelencsér-Horváth

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Xinze Li , Pengxu Chen , Yiyuan Wang , Weifeng Su , Wentao Cheng

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Jianyuan Wang , Minghao Chen , Nikita Karaev , Andrea Vedaldi , Christian Rupprecht , David Novotny

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yancheng Wang , Yingzhen Yang

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Seon-Ho Lee , Jue Wang , Zhikang Zhang , David Fan , Xinyu Li

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Renjie Pi , Lewei Yao , Jiahui Gao , Jipeng Zhang , Tong Zhang

This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Narges Norouzi , Svetlana Orlova , Daan de Geus , Gijs Dubbelman

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Dong Hoon Lee , Seunghoon Hong

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Dong Zhuo , Wenzhao Zheng , Jiahe Guo , Yuqi Wu , Jie Zhou , Jiwen Lu

Visual Geometry Grounded Transformer (VGGT) delivers state-of-the-art feed-forward 3D reconstruction, yet its global self-attention layer suffers from a drastic collapse phenomenon when the input sequence exceeds a few hundred frames:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Huan Li , Longjun Luo , Yuling Shi , Xiaodong Gu

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zichen Zou , Xiaosong Jia , Zuxuan Wu , Yu-Gang Jiang

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Rong Fan , Kaiyan Xiao , Minghao Zhu , Liuyi Wang , Kai Dai , Zhao Yang

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI
‹ Prev 1 2 3 10 Next ›