AI Paper Atlas

Research map / 3D vision / Human pose estimation

CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling

Binbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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 low-level convolutional visual features to pixel-aligned DINOv2 conditioning (ablation)Cupid refinement stage · Toys4K (sampled geometry and pose)PSNR: 27.74 -> 30.05Improved
add pose-aligned conditioning (DINOv2 latent volume) to TRELLIS baseline (ablation)Cupid refinement stage · Toys4K (GT geometry and pose)PSNR: 31.84 -> 32.37Improved
add DINOv2 positional embeddings to SLat latents (ablation)Cupid refinement stage · Toys4K (sampled geometry and pose)PSNR: 27.47 -> 27.56No clear effect
zero latents of occluded voxels in the input view (ablation)Cupid refinement stage · Toys4K (GT geometry and pose)PSNR: 32.37 -> 32.39No clear effect
zero latents of occluded voxels in the input view (ablation)Cupid refinement stage · Toys4K (sampled geometry and pose)PSNR: 27.85 -> 27.74No clear effect
use full pose-aligned conditioning with sampled stage-one outputs (ablation)Cupid · Toys4KPSNR: 27.47 -> 30.05Improved
jointly generate object and camera pose, then inject pixel-aligned features, instead of OnePoseGen post-hoc alignmentCupid · Toys4K input-view consistencyPSNR: 17.43 -> 30.05Improved
jointly generate object and camera pose instead of view-centric reconstruction (OpenLRM)Cupid · GSO monocular geometryChamfer Distance (avg): 3.741 -> 1.823Improved
compare Cupid to point-map regression methods that use only visible geometryCupid · Toys4K monocular geometryChamfer Distance (avg): 2.534 vs 1.144 (VGGT), 1.284 (MoGe)Hurt
use Cupid pixel-aligned conditioning instead of TRELLIS global conditioningTRELLIS · Toys4K novel-view CLIP score (ViT-B/16)CLIP image score: 0.9465 -> 0.9501Improved
add random occlusion masks on conditioning images during fine-tuningCupid · multi-object scenesscene reconstruction qualityImproved

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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