ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
This addresses the challenge of robust 3D shape generation in real-world scenarios for applications like robotics and AR/VR, though it is incremental as it builds on existing techniques like SLAM and transformers.
The paper tackles the problem of generating 3D shapes from casually captured image sequences, which often include occlusions and clutter, and presents ShapeR, a method that achieves a 2.7x improvement in Chamfer distance over state-of-the-art approaches.
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.