AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis

Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, Gim Hee Lee

ICCV 2021 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 158 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 ImageNet pre-training of the encoder (ablation)MINE N=32 · KITTIPSNR: 21.4 -> 21.6Improved
add ImageNet pre-training of the encoder (ablation)MINE N=32 · KITTILPIPS: 0.129 -> 0.122Improved
add edge-aware depth smoothness loss (ablation)MINE N=32 · KITTIPSNR: 21.6 -> 21.6No clear effect
add edge-aware depth smoothness loss (ablation)MINE N=32 · KITTILPIPS: 0.123 -> 0.122Improved
increase number of planes N from 32 to 256 (ablation)MINE (train 384x128) · KITTISSIM: 0.815 -> 0.828Improved
increase number of planes N from 32 to 256 (ablation)MINE (train 384x128) · KITTILPIPS: 0.122 -> 0.112Improved
increase number of planes N from 32 to 256 (ablation)MINE (train 384x128) · KITTIPSNR: 21.6 -> 21.9Improved
increase number of planes N from 32 to 64 (ablation)MINE (train 768x256) · KITTIPSNR: 21.4 -> 21.3No clear effect
increase number of planes N from 32 to 64 (ablation)MINE · RealEstate10K (random target)LPIPS: 0.1674 -> 0.1562Improved
increase number of planes N from 32 to 64 (ablation)MINE · RealEstate10K (random target)PSNR: 24.56 -> 24.50No clear effect
increase number of planes N from 32 to 64 (ablation)MINE · Flowers Light FieldsPSNR: 30.2 -> 30.3Improved
replace discrete-plane MPI with continuous-depth MINEMPI · RealEstate10K (random target)PSNR: 23.52 -> 24.56Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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