AI Paper Atlas

Research map / 3D vision / 3D generation

VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement

Tiancheng Fang, Bowen Pan, Lingxi Chen, Jiangjing Lyu, Chengfei Lv, Chaoyue Niu, Fan Wu

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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 Image Index spatial grounding (ablation)VIAFormer · Toys4k (VFM-derived, Pi3 input)IoU: 0.4176 -> 0.4460Improved
add Image Index spatial grounding (ablation)VIAFormer · Dora (VFM-derived, Pi3 input)IoU: 0.4418 -> 0.4585Improved
add Correctional Flow (refine VFM latent instead of noise) (ablation)VIAFormer · Toys4k (VFM-derived, Pi3 input)IoU: 0.3102 -> 0.4460Improved
add Correctional Flow (refine VFM latent instead of noise) (ablation)VIAFormer · Dora (VFM-derived, Pi3 input)IoU: 0.2675 -> 0.4585Improved
add single-image cross-attention conditioning to geometry-only self-attention (ablation)24-Layer transformer · Toys4k (VFM-derived, Pi3 input)IoU: 0.4111 -> 0.4255No clear effect
add single-image cross-attention conditioning to geometry-only self-attention (ablation)24-Layer transformer · Dora (VFM-derived, Pi3 input)IoU: 0.4285 -> 0.4356No clear effect
use VGGT-conditioned 4-view features with 3-layer MLP adapter instead of image cross-attention (ablation)24-Layer Cross-Attn · Toys4k (VFM-derived, Pi3 input)IoU: 0.4255 -> 0.4055No clear effect
use VGGT-conditioned 4-view features with 8-layer self-attention adapter instead of image cross-attention (ablation)24-Layer Cross-Attn · Toys4k (VFM-derived, Pi3 input)IoU: 0.4255 -> 0.4076No clear effect
use Voxel-Image Union-Space with Image Index instead of standard cross-attentionVIAFormer vs 24-Layer Cross-Attn · Toys4k (synthetic corruption)IoU: 0.2590 -> 0.8580Improved
use VIAFormer instead of Pi3 voxelization inputVFM-derived voxels · Toys4k (VFM-derived, Pi3 input)IoU: 0.3959 -> 0.4460Improved
use VIAFormer instead of Pi3 voxelization inputVFM-derived voxels · Dora (VFM-derived, Pi3 input)IoU: 0.4244 -> 0.4585Improved
increase number of input views beyond 3 to 4 (ablation)VIAFormer · Toys4k (view count study)IoUMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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