ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting
This addresses the problem of high-fidelity monocular 3D reconstruction for applications like computer vision and graphics, though it appears incremental as it builds on existing 3D Gaussian splatting methods.
The paper tackles the problem of generating 3D content from a single image, which is challenging due to occlusions and inconsistencies in synthesized auxiliary views, by proposing ERGO, an adaptive optimization framework that decomposes losses into excess risk and Bayes error to dynamically adjust weights. The result is enhanced geometric fidelity and textural quality in 3D reconstruction, with experiments on Google Scanned Objects and OmniObject3D datasets showing superiority over state-of-the-art methods.
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these views inevitably contain geometric inconsistencies and textural misalignments that propagate and amplify artifacts during 3D reconstruction. To effectively harness these imperfect supervisory signals, we propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO. Specifically, ERGO decomposes the optimization losses in 3D Gaussian splatting into two components, i.e., excess risk that quantifies the suboptimality gap between current and optimal parameters, and Bayes error that models the irreducible noise inherent in synthesized views. This decomposition enables ERGO to dynamically estimate the view-specific excess risk and adaptively adjust loss weights during optimization. Furthermore, we introduce geometry-aware and texture-aware objectives that complement the excess-risk-derived weighting mechanism, establishing a synergistic global-local optimization paradigm. Consequently, ERGO demonstrates robustness against supervision noise while consistently enhancing both geometric fidelity and textural quality of the reconstructed 3D content. Extensive experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.