AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors

Wenyuan Zhang, Kanle Shi, Yu-Shen Liu, Zhizhong Han

ECCV 2024 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 6 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
replace handcrafted renderer equations with a learned volume rendering priorUDF rendering · ShapeNet GT UDF renderingDepth-L1: 1.28 -> 0.41Improved
learned prior versus handcrafted renderers for UDF inference from RGBNeuralUDF/NeUDF · DeepFashion3DChamfer Distance: 2.01 -> 1.71Improved
use sampling interval instead of coordinates as prior input (ablation)volume rendering prior · DeepFashion3DCD-L1: 2.92 -> 1.71Improved
include sampling interval as input alongside unsigned distances (ablation)volume rendering prior · DeepFashion3DCD-L1: 1.87 -> 1.71Improved
train the prior with RGBD supervision instead of depth only (ablation)volume rendering prior · DeepFashion3DCD-L1: 1.71 -> 2.02Hurt
train the prior with RGB supervision only (ablation)volume rendering prior · DeepFashion3DCD-L1: DivergentHurt
fine-tune the prior with RGB images at test time (ablation)volume rendering prior · DeepFashion3DCD-L1: DivergentHurt
use more than two training shapes for the prior (ablation)volume rendering prior · DeepFashion3D and DTUChamfer Distance: 1.71 -> 1.72 (100 shapes)No clear effect
different choices of training shape pair (ablation)volume rendering prior · DeepFashion3DChamfer Distance: 1.71 to 1.78 across setsNo clear effect
neighboring window size 30 versus very small (1) or large (50) (ablation)volume rendering prior · DeepFashion3D example shapeChamfer Distance: 2.11 -> 1.59Improved
learn the prior for SDF instead of UDFvolume rendering prior · DeepFashion3D SDF exampleChamfer Distance: 0.73 -> 0.65Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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