Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks
This addresses the generalization and consistency limitations in neural 3D reconstruction for applications in computer vision and graphics, though it appears incremental as it builds on existing neural rendering and HyperNetwork techniques.
The paper tackles the ill-posed problem of single-view image-to-3D reconstruction by introducing Hyper-VolTran, a method that avoids scene-specific optimization and achieves consistent results with rapid generation.
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To overcome the limitations of existing approaches regarding generalization and consistency, we introduce a novel neural rendering technique. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Specifically, our method builds neural encoding volumes from generated multi-view inputs. We adjust the weights of the SDF network conditioned on an input image at test-time to allow model adaptation to novel scenes in a feed-forward manner via HyperNetworks. To mitigate artifacts derived from the synthesized views, we propose the use of a volume transformer module to improve the aggregation of image features instead of processing each viewpoint separately. Through our proposed method, dubbed as Hyper-VolTran, we avoid the bottleneck of scene-specific optimization and maintain consistency across the images generated from multiple viewpoints. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.