Novel View Synthesis using DDIM Inversion

arXiv:2508.10688 · cs.CV · Submitted 2025-08-14 · Read on arXiv

cs.CV

Submitted: 2025-08-14

Updated: 2026-10-10

Code: https://github.com/VisualConception-Group/ddim_nvs

Terminology

• Diffusion Model — 3× in this paper · explained in 9 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes

Sources

• FreeInv: Free Lunch for Improving DDIM Inversion
• A Fourier Space Perspective on Diffusion Models
• Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
• Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
• Magic-Boost: Boost 3D Generation with Multi-View Conditioned Diffusion
• Stereo Magnification: Learning View Synthesis using Multiplane Images

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models