AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

Aarush Gupta, Junli Cao, Chaoyang Wang, Ju Hu, Sergey Tulyakov, Jian Ren, Laszlo Attila Jeni

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Few-shot neural rendering architectures · 2 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
Use a ray-space grid encoder instead of frequency encoding (ablation)LightSpeed · Lego sub-scene, 15-layer decoderPSNR: 28.84 -> 30.37Improved
Use a ray-space grid encoder instead of frequency encoding (ablation)LightSpeed · Lego sub-scene, 30-layer decoderPSNR: 30.63 -> 31.70Improved
Use a ray-space grid encoder instead of frequency encoding (ablation)LightSpeed · Lego sub-scene, 60-layer decoderPSNR: 32.16 -> 32.34Improved
Represent rays with light-slab coordinates and grids instead of Plücker coordinates (ablation)LightSpeed · Lego sub-scene, 15-layer decoderPSNR: 28.65 -> 30.37Improved
Represent rays with light-slab coordinates and grids instead of Plücker coordinates (ablation)LightSpeed · Lego sub-scene, 30-layer decoderPSNR: 30.84 -> 31.70Improved
Represent rays with light-slab coordinates and grids instead of Plücker coordinates (ablation)LightSpeed · Lego sub-scene, 60-layer decoderPSNR: 32.14 -> 32.34Improved
Increase pseudo-data from 2k to 6k samples per Lego sub-scene (ablation)LightSpeed · Lego sub-scenePSNR: 30.44 -> 31.2Improved
Use a splitting plane at radius/√2 rather than radius/√3 (ablation)LightSpeed · Lego sub-scenePSNR: 30.23 -> 30.44Improved
Train the five scene partitions in parallelLightSpeed · Legotraining duration: 75 hours -> 15 hoursImproved
Use LightSpeed rather than MobileR2LNeural light field rendering · Synthetic 360°PSNR: 31.34 -> 32.23Improved
Use LightSpeed rather than MobileR2LNeural light field rendering · Forward-facingPSNR: 26.15 -> 26.50No clear effect

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