TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation
TransNormal-2 improves monocular surface-normal estimation by fixing VAE edge degradation with geometry-aware losses and refinement, matching MoGe-2 with 1.4% of annotations.
TransNormal-2 is a FLUX.2-based rectified-flow framework for monocular surface-normal estimation with single-step deterministic inference. The authors quantify that VAE 8x spatial compression introduces 1.3-8.5 degrees of mean angular error even on ground-truth normals, with edge error up to 2.8x the global error. The method adds geometry-aware pixel-space losses and an RGB-guided Geometric Refinement Module to correct boundary-localized decoding errors. It matches or exceeds MoGe-2 on all eight reported metrics using only 1.4% as many task-specific annotations, and cuts transparent-object MAE by 4.2 degrees on ClearGrasp and 3.1 degrees on ClearPose.
- Shows VAE encode-decode of ground-truth normals alone introduces 1.3-8.5 degrees of angular error
- Uses geometry-aware pixel-space losses plus an RGB-guided Geometric Refinement Module for edge correction
- Reduces transparent-object MAE by 4.2 degrees on ClearGrasp and 3.1 degrees on ClearPose
- Matches or exceeds MoGe-2 using only 1.4% as many task-specific normal annotations
- Products
- TransNormal-2FLUX.2MoGe-2
From the original article
1 min read at huggingface.co
Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE reconstruction degradation. The 8x spatial compression in the VAE encoder-decoder degrades surface normals at object boundaries; even encoding and decoding ground-truth normals introduces 1. 3--8.
By Mingwei Li, Yi Yang, Hehe Fan · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.