AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields

Yonggan Fu, Huaizhi Qu, Zhifan Ye, Chaojian Li, Kevin Zhao, Yingyan (Celine) Lin

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 1 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
reuse RGB blending weights to blend 2D predictions (predict-then-blend) instead of predicting on rendered images (ablation)Omni-Recon · ScanNet zero-shot semantic segmentationmIoU: 41.32 -> 61.11Improved
predict-then-blend instead of render-then-predict (ablation)Omni-Recon · Replica zero-shot semantic segmentationmIoU: 15.64 -> 32.11Improved
predict-then-blend instead of render-then-predict (ablation)Omni-Recon · ScanNet keypoint 3Dl1 error: 0.0412 -> 0.0197Improved
add LoRA parameter-efficient tuning on top of zero-shotOmni-Recon · ScanNet semantic segmentationmIoU: 61.11 -> 62.35Improved
add LoRA PET to edge and keypoint tasksOmni-Recon · ScanNet edge detectionl1 error: 0.0434 -> 0.0342Improved
finetune mesh and shader with differentiable rendering for 10 secondsOmni-Recon real-time pipeline · DTUPSNR (mean): 22.96 -> 25.68Improved
longer finetuning (1 min to 5 min) of mesh and shaderOmni-Recon real-time pipeline · DTUPSNR (mean): 28.34 -> 29.02Improved
bake geometry branch into mesh and use appearance branch as shader (Nvdiffrast)Omni-Recon · DTUFPS: 0.024 (ReTR) -> 71.3Improved
transformer geometry branch with progressive fusion, versus prior generalizable reconstructionOmni-Recon · DTU sparse-view reconstructionmean Chamfer distance: 1.17 -> 1.13Improved
Omni-Recon versus ReTR on novel view renderingOmni-Recon · DTU novel view renderingPSNR (mean): 25.59 -> 26.32Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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