AI Paper Atlas

Research map / Point clouds / Point cloud classification

CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

Hajin Shim, Changhun Kim, Eunho Yang

ECCV 2024 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 6 citations (OpenAlex)

This paper tried a common change: Larger batch size

increase batch size from 1 to 64 for CloudFixer-O vs MATE · ModelNet40-C (PointMAE) · average accuracy (%): to 72.68 Improved

What 785 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
tailor input adaptation to point clouds (geometric transform with Chamfer objective) instead of 2D-style DDADDA · ModelNet40-C (batch size 1)average accuracy (%): 74.37 -> 78.23Improved
avoid backpropagation through diffusion model and long generationDDA · ModelNet40-Cadaptation time per sample (s): 23.6 -> 0.93Improved
add voting over K=5 transformations (ablation)CloudFixer · ModelNet40-C (batch size 1)average accuracy (%): 78.23 -> 79.09Improved
entropy-minimization TTA (TENT, SHOT) under batch size 1Point2Vec · ModelNet40-C (batch size 1)average accuracy (%): 62.09 -> 4.29 (TENT)Hurt
entropy-minimization and pseudo-label TTA on label-sorted non-i.i.d. streamPoint2Vec · ModelNet40-C (non-i.i.d. label-sorted stream)average accuracy (%): 60.38 -> 12.80 (TENT)Hurt
add online model adaptation with consistency loss (CloudFixer-O) under batch size 64Point2Vec · ModelNet40-C (batch size 64, i.i.d.)average accuracy (%): 78.85 (TENT) -> 81.49Improved
increase batch size from 1 to 64 for CloudFixer-O vs MATE (ablation)CloudFixer-O · ModelNet40-C (PointMAE)average accuracy (%): to 72.68Improved
increase MATE update steps (ablation)MATE · ModelNet40-C (PointMAE)average accuracy (%): saturates at approximately 61%No clear effect
use small diffusion timestep range t in [0.01T, 0.02T] (ablation)CloudFixer · ModelNet40-Caverage accuracyHurt
use large diffusion timestep range t in [0.4T, 0.5T] (ablation)CloudFixer · ModelNet40-Caverage accuracyHurt
replace rotation with affine matrix or remove parameterization (ablation)CloudFixer · ModelNet40-Caverage accuracyHurt
use squared l2 or diffusion noise-matching loss instead of Chamfer distance (ablation)CloudFixer · ModelNet40-Caverage accuracyHurt

Later papers that compared with this method

1 later accepted paper reports CloudFixer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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