ShapeR: Robust Conditional 3D Shape Generation from Casual Captures

TL;DR

ShapeR is a robust method for generating high-quality 3D object shapes from casual, real-world image sequences by leveraging multi-modal data and advanced training techniques, outperforming existing methods significantly.

Contribution

We introduce ShapeR, a novel framework that effectively generates 3D shapes from casual captures using multi-modal data and robust training strategies, with a new in-the-wild evaluation benchmark.

Findings

Outperforms existing methods with 2.7x better Chamfer distance

Successfully handles cluttered backgrounds and unstructured data

Achieves high-fidelity 3D shapes from casual image sequences

Abstract

Recent advances in 3D shape generation have achieved impressive results, but most existing methods rely on clean, unoccluded, and well-segmented inputs. Such conditions are rarely met in real-world scenarios. We present ShapeR, a novel approach for conditional 3D object shape generation from casually captured sequences. Given an image sequence, we leverage off-the-shelf visual-inertial SLAM, 3D detection algorithms, and vision-language models to extract, for each object, a set of sparse SLAM points, posed multi-view images, and machine-generated captions. A rectified flow transformer trained to effectively condition on these modalities then generates high-fidelity metric 3D shapes. To ensure robustness to the challenges of casually captured data, we employ a range of techniques including on-the-fly compositional augmentations, a curriculum training scheme spanning object- and scene-level datasets, and strategies to handle background clutter. Additionally, we introduce a new evaluation benchmark comprising 178 in-the-wild objects across 7 real-world scenes with geometry annotations. Experiments show that ShapeR significantly outperforms existing approaches in this challenging setting, achieving an improvement of 2.7x in Chamfer distance compared to state of the art.