AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li, Shenxing Wei, Zhixuan Sun, Bo Yang

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 0 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
add object candidate discerning module (ablation)EvObj-VAE · ScanNet val (chair)AP: 45.0 -> 55.0Improved
add evolving optimization of discerning module (ablation)EvObj-VAE · ScanNet val (chair)AP: 52.2 -> 55.0Improved
add synthetic pretraining of discerning module (ablation)EvObj-VAE · ScanNet val (chair)AP: 37.4 -> 55.0Improved
add object completion module (ablation)EvObj-VAE · ScanNet val (chair)AP: 33.8 -> 55.0Improved
evolving interval T=50 instead of 100 (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 52.6Hurt
evolving interval T=200 instead of 100 (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 53.4Hurt
use PoinTr instead of AdaPoinTr for completion (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 53.1No clear effect
use SnowflakeNet instead of AdaPoinTr for completion (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 54.1No clear effect
use PointNet++ instead of SparseUNet for discerning module (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 54.5No clear effect
Chamfer threshold 0.08 instead of 0.10 (ablation)EvObj-VAE · ScanNet val (chair)AP: 55.0 -> 48.0Hurt
apply discerning module as plug-and-play refinementUnScene3D · ScanNet val (chair)AP: 37.2 -> 41.1Improved
apply discerning module as plug-and-play refinementPart2Object · ScanNet val (chair)AP: 34.4 -> 39.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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