RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses

arXiv — cs.CV•Wednesday, November 12, 2025 at 5:00:00 AM

The publication of 'RePose-NeRF' marks a significant advancement in the field of 3D reconstruction, which is crucial for various robotic tasks such as navigation and environment understanding. Traditional methods struggle with the accuracy of camera poses, especially in real-world scenarios, limiting their effectiveness. The proposed framework overcomes these challenges by jointly refining camera poses while learning an implicit scene representation, resulting in high-quality, editable 3D meshes. These meshes are compatible with common 3D graphics and robotics tools, bridging the gap between neural implicit representations and practical applications. Experiments on standard benchmarks confirm the method's robustness and accuracy under pose uncertainty, highlighting its potential to enhance robotic capabilities.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.LGa day ago

Understanding World or Predicting Future? A Comprehensive Survey of World Models

NeutralArtificial Intelligence

The article discusses the growing interest in world models, particularly in the context of advancements in multimodal large language models like GPT-4 and video generation models such as Sora. It provides a comprehensive review of the literature on world models, which serve to either understand the current state of the world or predict future dynamics. The review categorizes world models based on their functions: constructing internal representations and predicting future states, with applications in generative games, autonomous driving, robotics, and social simulacra.

Read full article

via arXiv — cs.LG

arXiv — cs.CV2 days ago

One-to-N Backdoor Attack in 3D Point Cloud via Spherical Trigger

PositiveArtificial Intelligence

Backdoor attacks pose a significant risk to deep learning systems, especially in critical 3D applications like autonomous driving and robotics. This study introduces a novel one-to-N backdoor framework for 3D vision, utilizing a configurable spherical trigger. The research demonstrates that a single trigger can effectively encode multiple target classes, achieving high attack success rates of up to 100% while preserving accuracy on clean data.

Read full article

via arXiv — cs.CV

arXiv — cs.LG2 days ago

SURFACEBENCH: Can Self-Evolving LLMs Find the Equations of 3D Scientific Surfaces?

NeutralArtificial Intelligence

The article discusses the introduction of SurfaceBench, a new benchmark for symbolic surface discovery in machine learning. This benchmark addresses the challenge of equation discovery from data, which is crucial for understanding complex physical and geometric phenomena. SurfaceBench includes 183 tasks across 15 categories of symbolic complexity, featuring various equation representation forms and synthetic three-dimensional data. It aims to improve upon existing benchmarks that often focus on scalar functions and rely on inadequate metrics.

Read full article

via arXiv — cs.LG