paper-with-me

홈 › Papers

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers

2025-11-18 · Yutian Chen, Yuheng Qiu, Ruogu Li, Ali Agha, Shayegan Omidshafiei, Jay Patrikar, Sebastian Scherer arxiv

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 uncertainty and selectively merge low-confidence ones, effectively reducing computation while maintaining spatial coverage. Compared to similarity-based merging or pruning, the confidence signal in Co-Me reliably indicates regions emphasized by the transformer, enabling substantial acceleration without degrading performance. Co-Me applies seamlessly to various multi-view and streaming visual geometric transformers, achieving speedups that scale with sequence length. When applied to VGGT and Pi3, Co-Me achieves up to 21.5x and 20.4x speedup, making visual geometric transformers practical for real-time 3D perception and reconstruction.

📄 PDF Abstract BibTeX arXiv:2511.14751

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

2025-12-04 · Zhijian Shu, Cheng Lin, Tao Xie, Wei Yin 외 arxiv

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 l…

3D Reconstruction

SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering

2026-03-31 · Wenli Li, Kai Zhao, Haoran Jiang, Enquan Yang 외 arxiv

Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed…

Question Answering

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

2026-08-20 · Bowen Cui, Weijie Wang, Zeyu Zhang, Yefei He 외 arxiv

While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete shape tokens autoregressively or iterative…

3D Generation

Local Representative Token Guided Merging for Text-to-Image Generation

2025-07-17 · Min-Jeong Lee, Hee-Dong Kim, Seong-Whan Lee arxiv

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging met…

Text-to-Image GenerationComputational Efficiency

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning

2026-05-19 · Pengtao Ma, Ziliang Zhou, Ciyu Ruan, Haoyang Wang 외 arxiv

First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs makes dense visual tokens computationall…

Spatial Reasoning