Paper Detail

TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation

Mingwei Li, Yi Yang, Hehe Fan

huggingface Score 8.0

Published 2026-09-06 · First seen 2026-09-09

General AI

Abstract

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--8.5° of mean angular error (MAE), with edge MAE reaching 2.8x the global MAE. We present TransNormal-2, a FLUX.2-based rectified-flow framework with single-step deterministic inference that addresses this degradation on both sides of the VAE decoder: in how latent predictions are supervised during training, and in how decoded normals are corrected at inference. First, geometry-aware pixel-space losses, including inverse rendering self-consistency, von~Mises-Fisher angular loss, and wavelet edge-aware regularization, complement latent MSE by enforcing spherical normal geometry and diffuse image-formation cues after VAE decoding. Second, a lightweight Geometric Refinement Module (GRM) applies an RGB-guided residual correction to reduce boundary-localized decoding errors without freely rewriting the coarse prediction. On general-scene benchmarks, TransNormal-2 matches or exceeds MoGe-2 on all eight reported metrics while using only 1.4% as many task-specific normal annotations. The gains are clearest for transparent objects, reducing MAE by 4.2° on ClearGrasp and 3.1° on ClearPose over the strongest prior baselines. Code will be released at https://longxiang-ai.github.io/TransNormal-2.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{li2026transnormal,
  title = {TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation},
  author = {Mingwei Li and Yi Yang and Hehe Fan},
  year = {2026},
  abstract = {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--8.5° of mean angular error (MAE), with edge MAE reaching 2.8x the global MAE. We present TransNormal-2, a FLUX.2-based rectified-flow framework with single-st},
  url = {https://huggingface.co/papers/2609.06665},
  keywords = {rectified-flow, VAE reconstruction, inverse rendering self-consistency, von Mises-Fisher angular loss, wavelet edge-aware regularization, Geometric Refinement Module, RGB-guided residual correction, code available, huggingface daily},
  eprint = {2609.06665},
  archiveprefix = {arXiv},
}

Metadata

{}