Research map / 3D vision / NeRF and radiance fields
Learning to Dodge A Bullet: Concyclic View Morphing via Deep Learning
Shi Jin, Ruiynag Liu, Yu Ji, Jinwei Ye, Jingyi Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the middle reference image as encoder input (three images instead of two) (ablation) | CVMN · SURREAL | MAE: 2.039 -> 1.453 | Improved |
| add the middle reference image as encoder input (three images instead of two) (ablation) | CVMN · SURREAL | SSIM: 0.966 -> 0.983 | Improved |
| keep middle image only as encoder input rather than also predicting and blending it in the decoders (ablation) | CVMN · SURREAL | MAE: 2.175 -> 1.453 | Improved |
| keep middle image only as encoder input rather than also predicting and blending it in the decoders (ablation) | CVMN · SURREAL | SSIM: 0.967 -> 0.983 | Improved |
| use CVMN with cyclic rectification and three views instead of Deep View Morphing | view morphing · SURREAL | MAE: 3.315 -> 1.453 | Improved |
| use CVMN instead of DVM | view morphing · ShapeNet car | MAE: 3.441 -> 1.608 | Improved |
| use CVMN instead of DVM | view morphing · ShapeNet chair | MAE: 5.579 -> 2.777 | Improved |
| use CVMN instead of TVSN | view synthesis · ShapeNet chair | MAE: 10.02 -> 2.777 | Improved |
Closest papers by meaning
- Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.83)
- BulletTime: Decoupled Control of Time and Camera Pose for Video Generation (CVPR 2026 · similarity 0.83)
- DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting (ECCV 2024 · similarity 0.83)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.82)
- Generative Perception of Shape and Material from Differential Motion (NeurIPS 2025 · similarity 0.82)
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
