AI Paper Atlas

Research map / 3D vision / 3D generation

PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm

Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Tong He, Wanli Ouyang

TPAMI 2025 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 62 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 depth rendering supervision alongside color (ablation)Ponder-RGBD VoteNet · ScanNet 3D detectionmAP@50: 40.5 -> 41.0Improved
add color rendering supervision alongside depth (ablation)Ponder-RGBD VoteNet · ScanNet 3D detectionmAP@50: 40.9 -> 41.0Improved
use five input views instead of one (ablation)Ponder-RGBD VoteNet · ScanNet 3D detectionmAP@50: 40.1 -> 41.0Improved
use five input views instead of one (ablation)Ponder-RGBD VoteNet · SUN RGB-D 3D detectionmAP@50: 35.4 -> 36.6Improved
use 75% mask ratio instead of no masking (ablation)Ponder-RGBD VoteNet · ScanNet 3D detectionmAP@50: 40.7 -> 41.7Improved
remove masking entirely (0% mask ratio) (ablation)Ponder-RGBD VoteNet · SUN RGB-D 3D detectionmAP@50: 37.3 vs 37.0 at 75%No clear effect
use multi-resolution feature volume 16+32+64 instead of 16 only (ablation)Ponder-RGBD VoteNet · ScanNet 3D detectionmAP@50: 40.7 -> 41.0No clear effect
use mask ratio 0.3 for camera images instead of 0.1 (ablation)PonderV2 UVTR-C · nuScenesNDS: 31.9 -> 32.9Improved
increase decoder depth from (2,2) to (6,4) (ablation)PonderV2 UVTR-C · nuScenesNDS: 31.3 -> 32.9Improved
increase decoder width from 32 to 256 (ablation)PonderV2 UVTR-C · nuScenesNDS: 32.9 -> 32.4No clear effect
use NeuS rendering instead of UniSurf (ablation)PonderV2 UVTR-C · nuScenesNDS: 32.5 -> 32.9Improved
use NeuS rendering instead of VolSDF (ablation)PonderV2 UVTR-C · nuScenesNDS: 32.8 -> 32.9No clear effect

Later papers that compared with this method

1 later accepted paper reports Ponder-v2† 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