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

  • 类型：arxiv
  • 标识：2609.06665
  • 链接：https://arxiv.org/abs/2609.06665
  • 主分类：multimodal
  • 形态：method
  • TLDR：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
  • 待LLM分类：否
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-09-agent-rag-longcontext-candidates.json