Speedy MASt3R
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 scheme that accelerates matching by orders of magnitude while preserving theoretical guarantees. This approach has gained strong traction, with DUSt3R and MASt3R collectively cited over 250 times in a short span, underscoring their impact. However, despite its accuracy, MASt3R's inference speed remains a bottleneck. On an A40 GPU, latency per image pair is 198.16 ms, mainly due to computational overhead from the ViT encoder-decoder and Fast Reciprocal Nearest Neighbor (FastNN) matching. To address this, we introduce Speedy MASt3R, a post-training optimization framework that enhances inference efficiency while maintaining accuracy. It integrates multiple optimization techniques, including FlashMatch-an approach leveraging FlashAttention v2 with tiling strategies for improved efficiency, computation graph optimization via layer and tensor fusion having kernel auto-tuning with TensorRT (GraphFusion), and a streamlined FastNN pipeline that reduces memory access time from quadratic to linear while accelerating block-wise correlation scoring through vectorized computation (FastNN-Lite). Additionally, it employs mixed-precision inference with FP16/FP32 hybrid computations (HybridCast), achieving speedup while preserving numerical precision. Evaluated on Aachen Day-Night, InLoc, 7-Scenes, ScanNet1500, and MegaDepth1500, Speedy MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy. This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Scene ReconstructionGPUMixed RealityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SpeedyIBL: A Comprehensive, Precise, and Fast Implementation of Instance-Based Learning Theory
Instance-Based Learning Theory (IBLT) is a comprehensive account of how humans make decisions from experience during dynamic tasks. Since it was first proposed almost two decades ago, multiple computational models have b…
Decision MakingLearning TheoryTraining Large-Scale News Recommenders with Pretrained Language Models in the Loop
News recommendation calls for deep insights of news articles' underlying semantics. Therefore, pretrained language models (PLMs), like BERT and RoBERTa, may substantially contribute to the recommendation quality. However…
ArticlesNews RecommendationRecommendation SystemsGeneralized Speedy Q-learning
In this paper, we derive a generalization of the Speedy Q-learning (SQL) algorithm that was proposed in the Reinforcement Learning (RL) literature to handle slow convergence of Watkins' Q-learning. In most RL algorithms …
Q-LearningReinforcement LearningReinforcement Learning (RL)Speedy Object Detection based on Shape
This study is a part of design of an audio system for in-house object detection system for visually impaired, low vision personnel by birth or by an accident or due to old age. The input of the system will be scene and o…
Objectobject-detectionObject DetectionMomentum-based Accelerated Q-learning
This paper studies accelerated algorithms for Q-learning. We propose an acceleration scheme by incorporating the historical iterates of the Q-function. The idea is conceptually inspired by the momentum-based acceleration…
Atari GamesQ-Learning