Recovering 3D Shapes from Ultra-Fast Motion-Blurred Images

2026-02-08

AI Summary

This work addresses the challenge of recovering three-dimensional geometry from single images under extreme motion blur, a scenario where traditional multi-view stereo methods fail. The authors propose a differentiable inverse rendering framework that jointly optimizes 3D geometry while explicitly modeling ultra-fast motion blur. Central to their approach is an efficient barycentric coordinate solver that drastically reduces the computational cost of blur rendering and enables end-to-end differentiable optimization. Experimental results demonstrate that the method effectively reconstructs accurate 3D shapes under both high-speed translational and rotational motion, achieving up to a 4.57× speedup in rendering compared to prior approaches, thereby validating its efficacy and photorealistic fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We consider the problem of 3D shape recovery from ultra-fast motion-blurred images. While 3D reconstruction from static images has been extensively studied, recovering geometry from extreme motion-blurred images remains challenging. Such scenarios frequently occur in both natural and industrial settings, such as fast-moving objects in sports (e.g., balls) or rotating machinery, where rapid motion distorts object appearance and makes traditional 3D reconstruction techniques like Multi-View Stereo (MVS) ineffective. In this paper, we propose a novel inverse rendering approach for shape recovery from ultra-fast motion-blurred images. While conventional rendering techniques typically synthesize blur by averaging across multiple frames, we identify a major computational bottleneck in the repeated computation of barycentric weights. To address this, we propose a fast barycentric coordinate solver, which significantly reduces computational overhead and achieves a speedup of up to 4.57x, enabling efficient and photorealistic simulation of high-speed motion. Crucially, our method is fully differentiable, allowing gradients to propagate from rendered images to the underlying 3D shape, thereby facilitating shape recovery through inverse rendering. We validate our approach on two representative motion types: rapid translation and rotation. Experimental results demonstrate that our method enables efficient and realistic modeling of ultra-fast moving objects in the forward simulation. Moreover, it successfully recovers 3D shapes from 2D imagery of objects undergoing extreme translational and rotational motion, advancing the boundaries of vision-based 3D reconstruction. Project page: https://maxmilite.github.io/rec-from-ultrafast-blur/

Problem

• 3D shape recovery
• motion blur
• ultra-fast motion
• inverse rendering
• 3D reconstruction

Innovation

• inverse rendering
• motion blur
• 3D shape recovery
• differentiable rendering
• barycentric coordinates