AI Paper Atlas

Research map / 3D vision / Face and shape

MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction

Dehao Hao, Kaiyi Zhang, Tanghui Jia, Xiangjun Gao, Dongyu Yan, Weikai Chen, Zeyu HU, Lingting Zhu, Yingda Yin, Runze Zhang, Li Yuan, Xin Wang and 1 more

ECCV 2026 · 3D vision › Face and shape · approach: Textured mesh generation · 2 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 multi-scale query decoding (ablation)MSVS-VAE · ObjaverseMesh Distance (x10^4): 1.690 -> 1.395Improved
add multi-scale query decoding (ablation)MSVS-VAE · ObjaverseF1@0.001: 99.322 -> 99.621Improved
add multi-scale query decoding (ablation)MSVS-VAE · in-the-wildMesh Distance (x10^4): 1.626 -> 1.231Improved
add hierarchical point-shuffle upsampling (ablation)MSVS-VAE · ObjaverseMesh Distance (x10^4): 3.693 -> 1.690Improved
add hierarchical point-shuffle upsampling (ablation)MSVS-VAE · ObjaverseF1@0.001: 93.281 -> 99.322Improved
add hierarchical point-shuffle upsampling (ablation)MSVS-VAE · in-the-wildF1@0.001: 90.675 -> 99.416Improved
replace global cross-attention with AVS-ConvMSVS-VAE vs Lattice · query latency, 40k tokenslatency (ms): 3068.05 -> 213.29 (14.4x)Improved
increase token budget at inference (ablation)MSVS-VAE · ObjaverseMesh Distance (x10^4): 5.644 -> 1.395 (4k to 40k tokens)Improved
use MSVS-VAE instead of Lattice at 4k tokensMSVS-VAE · ObjaverseMesh Distance (x10^4): 11.502 -> 5.644Improved
use MSVS-VAE 20k instead of SparseFlex-1024 (210k tokens)MSVS-VAE · ObjaverseMesh Distance (x10^4): 2.165 -> 1.695Improved
use MSVS-VAE-40K instead of SparseFlex on Dora-Bench Level-4 S-MDMSVS-VAE-40K · Dora-Bench Level-4S-MD (x10^4): 3.08 -> 3.15Hurt

Earlier methods this paper compares with

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