Floating No More: Object-Ground Reconstruction from a Single Image
This addresses a limitation in 3D-aware image editing applications like shadow rendering and object pose manipulation, but it is incremental as it builds on existing single-image 3D reconstruction techniques.
The paper tackles the problem of 3D object reconstruction from single images, where objects often appear floating or tilted due to inaccurate object-ground-camera relations, and introduces ORG to reconstruct object geometry with the ground surface, improving shadow generation and pose manipulation quality.
Recent advancements in 3D object reconstruction from single images have primarily focused on improving the accuracy of object shapes. Yet, these techniques often fail to accurately capture the inter-relation between the object, ground, and camera. As a result, the reconstructed objects often appear floating or tilted when placed on flat surfaces. This limitation significantly affects 3D-aware image editing applications like shadow rendering and object pose manipulation. To address this issue, we introduce ORG (Object Reconstruction with Ground), a novel task aimed at reconstructing 3D object geometry in conjunction with the ground surface. Our method uses two compact pixel-level representations to depict the relationship between camera, object, and ground. Experiments show that the proposed ORG model can effectively reconstruct object-ground geometry on unseen data, significantly enhancing the quality of shadow generation and pose manipulation compared to conventional single-image 3D reconstruction techniques.