TurboVGGT uses adaptive sparse global attention with varying sparsity levels across frames and layers plus frame attention to enable faster multi-view 3D reconstruction while keeping competitive quality versus prior state-of-the-art methods.
Speed3r: Sparse feed-forward 3d reconstruction models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
Lite3R cuts latency by 1.7-2.0x and memory by 1.9-2.4x in feed-forward 3D reconstruction using sparse linear attention and FP8-aware quantization-aware training while keeping competitive quality on backbones like VGGT and DA3-Large.
citing papers explorer
-
TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
TurboVGGT uses adaptive sparse global attention with varying sparsity levels across frames and layers plus frame attention to enable faster multi-view 3D reconstruction while keeping competitive quality versus prior state-of-the-art methods.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
-
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
Lite3R cuts latency by 1.7-2.0x and memory by 1.9-2.4x in feed-forward 3D reconstruction using sparse linear attention and FP8-aware quantization-aware training while keeping competitive quality on backbones like VGGT and DA3-Large.