Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features

About

We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds). Our method distills diffusion features from image foundational models onto input shapes. Specifically, we use the input shapes to produce depth and normal maps as guidance for conditional image synthesis. In the process, we produce (diffusion) features in 2D that we subsequently lift and aggregate on the original surface. Our key observation is that even if the conditional image generations obtained from multi-view rendering of the input shapes are inconsistent, the associated image features are robust and, hence, can be directly aggregated across views. This produces semantic features on the input shapes, without requiring additional data or training. We perform extensive experiments on multiple benchmarks (SHREC'19, SHREC'20, FAUST, and TOSCA) and demonstrate that our features, being semantic instead of geometric, produce reliable correspondence across both isometric and non-isometrically related shape families. Code is available via the project page at https://diff3f.github.io/

Niladri Shekhar Dutt, Sanjeev Muralikrishnan, Niloy J. Mitra• 2023

Related benchmarks

TaskDatasetResultRank
3D Shape CorrespondenceFAUST remeshed (test)
Mean Geodesic Error (x100)20.7
65
Shape MatchingSCAPE remeshed (test)
Mean Geodesic Error (x100)22.1
46
Shape MatchingSHREC19 remeshed (test)
Mean Geodesic Error0.263
37
Non-isometric 3D shape matchingSMAL
Mean Geodesic Error0.284
22
Shape correspondence estimationTOPKIDS
Geodesic Error (x100)31
19
Shape CorrespondenceSHREC'20 (test)
Accuracy72.6
10
Inter-class shape matchingTOSCA (test)
Avg Geodesic Error0.45
7
Inter-class shape matchingSHREC07 (test)
Avg Geodesic Error0.5
7
Inter-class shape matchingSNIS (test)
Average Geodesic Error0.57
7
Shape CorrespondenceSHREC'19 Remeshed (test)
Accuracy26.41
5
Showing 10 of 13 rows

Other info

Code

Follow for update