Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
This addresses the problem of noisy priors in sparse view synthesis for 3D computer vision applications, representing a novel methodological improvement.
The paper tackles novel view synthesis from sparse inputs by proposing a 3D Gaussian Splatting method that uses binocular stereo consistency for self-supervision instead of external priors, achieving state-of-the-art performance on multiple datasets.
Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising quality and efficiency compared to the NeRF based methods. However, the neural priors from 2D pretrained models are often noisy and blurry, which struggle to precisely guide the learning of radiance fields. In this paper, We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting that does not require external prior as supervision. Our key idea lies in exploring the self-supervisions inherent in the binocular stereo consistency between each pair of binocular images constructed with disparity-guided image warping. To this end, we additionally introduce a Gaussian opacity constraint which regularizes the Gaussian locations and avoids Gaussian redundancy for improving the robustness and efficiency of inferring 3D Gaussians from sparse views. Extensive experiments on the LLFF, DTU, and Blender datasets demonstrate that our method significantly outperforms the state-of-the-art methods.