Anything-3D: Towards Single-view Anything Reconstruction in the Wild

TL;DR

Anything-3D introduces a novel framework combining visual-language models and segmentation techniques to enable accurate single-view 3D object reconstruction in diverse real-world scenarios.

Contribution

The paper presents a new method that integrates multiple models for reliable single-view 3D reconstruction, addressing limitations of previous approaches.

Findings

Produces detailed 3D reconstructions for various objects

Demonstrates robustness across diverse datasets

Outperforms existing methods in accuracy

Abstract

3D reconstruction from a single-RGB image in unconstrained real-world scenarios presents numerous challenges due to the inherent diversity and complexity of objects and environments. In this paper, we introduce Anything-3D, a methodical framework that ingeniously combines a series of visual-language models and the Segment-Anything object segmentation model to elevate objects to 3D, yielding a reliable and versatile system for single-view conditioned 3D reconstruction task. Our approach employs a BLIP model to generate textural descriptions, utilizes the Segment-Anything model for the effective extraction of objects of interest, and leverages a text-to-image diffusion model to lift object into a neural radiance field. Demonstrating its ability to produce accurate and detailed 3D reconstructions for a wide array of objects, \emph{Anything-3D\footnotemark[2]} shows promise in addressing the limitations of existing methodologies. Through comprehensive experiments and evaluations on various datasets, we showcase the merits of our approach, underscoring its potential to contribute meaningfully to the field of 3D reconstruction. Demos and code will be available at \href{https://github.com/Anything-of-anything/Anything-3D}{https://github.com/Anything-of-anything/Anything-3D}.