MVDiff: Scalable and Flexible Multi-view Diffusion for 3D Object Reconstruction from Single-View

Emmanuelle Bourigault, Pauline Bourigault; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 7579-7586

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally incorporating 3D representations into diffusion model decrease the model's speed as well as generalizability and quality. This paper proposes a general framework to generate consistent multi-view images from single image or leveraging scene representation transformer and view-conditioned diffusion model. In the model we introduce epipolar geometry constraints and multi-view attention to enforce 3D consistency. From as few as one image input our model is able to generate 3D meshes surpassing baselines methods in evaluation metrics including PSNR SSIM and LPIPS.