AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Monocular Neural Image Based Rendering With Continuous View Control

Xu Chen, Jie Song, Otmar Hilliges

ICCV 2019 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 60 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the transforming auto-encoder (explicit latent rotation) instead of concatenating the viewpoint (ablation)Ours · ShapeNet carL1 error: 0.045 -> 0.039Improved
add the transforming auto-encoder instead of concatenating the viewpoint (ablation)Ours · ShapeNet chairL1 error: 0.065 -> 0.056Improved
add depth-guided appearance warping instead of direct flow prediction (ablation)Ours · ShapeNet carL1 error: 0.052 -> 0.039Improved
add depth-guided appearance warping instead of direct flow prediction (ablation)Ours · ShapeNet chairL1 error: 0.066 -> 0.056Improved
add the transforming auto-encoder (ablation)Ours · ShapeNet carSSIM: 0.943 -> 0.949Improved
add depth-guided appearance warping (ablation)Ours · ShapeNet carSSIM: 0.932 -> 0.949Improved
add depth-guided warping (depth prediction before flow) (ablation)Ours · ShapeNet car flow predictionaccuracy: 76.3% -> 85.7%Improved
add the transforming auto-encoder (ablation)Ours · ShapeNet car flow predictionaccuracy: 84.6% -> 85.7%Improved
add the transforming auto-encoder (ablation)Ours · ShapeNet car depth predictionaccuracy: 89.0% -> 91.1%Improved
add the transforming auto-encoder (ablation)Ours · ShapeNet car flow predictionL1 error: 0.022 -> 0.021No clear effect
add the transforming auto-encoder (ablation)Ours · ShapeNet car depth predictionL1 error: 0.134 -> 0.132No clear effect
predict depth then project to flow instead of regressing flow directly and trained on flow baseline (Zhou et al.)Ours (w/o depth) · ShapeNet car flow predictionaccuracy: 69.1% -> 76.3%Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy