AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization

Weihang Liu, Xue Xian Zheng, Jingyi Yu, Xin Lou

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 5 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
learn bitwidth per layer and per scene with A-CAQ instead of fixed bitwidth for all (ablation)Instant-NGP quantization · Synthetic-NeRF (MDL)FQR: 14.00 -> 7.76Improved
add layer-wise quantization (Ours 1d vs fixed 1a) (ablation)Instant-NGP quantization · Synthetic-NeRF (MDL)PSNR: 31.56 -> 32.30Improved
add scene-wise bitwidth to layer-wise A-CAQ (ablation)A-CAQ · Synthetic-NeRF (MDL)FQR: 8.93 -> 7.76Improved
add bitwidth loss L_bit (adversarial bitwidth search) (ablation)A-CAQ · Synthetic-NeRF (MGL)FQR: 6.60 -> 5.33Improved
add QAT training (L_NeRF) on top of bitwidth search (ablation)A-CAQ · Synthetic-NeRF (MGL)FQR: 6.43 -> 5.33Improved
post-training with L_NeRF on fixed bitwidth (ablation)PTQ baseline · Synthetic-NeRF (MGL)PSNR: 22.29 -> 25.06Improved
A-CAQ vs LSQ+ under metric-guided (resource-constrained) learningInstant-NGP · Synthetic-NeRF MGL 10^-3PSNR: 20.26 -> 25.96Improved
A-CAQ vs LSQ+ under high-fidelity MDL settingInstant-NGP · Synthetic-NeRF MDLPSNR: FQR 9.60 -> 7.76; PSNR 32.11 -> 32.00Mixed
A-CAQ quantization vs full-precision Instant-NGPInstant-NGP · Synthetic-NeRF MDLBitOps (T): 71.01 -> 6.55Improved

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