OpenCodePapers

surface-normals-estimation-on-sintel

Surface Normals Estimation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodemAEModelNameReleaseDate
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation✓ Link28.7Marigold V2 (normals)2026-09-08
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation✓ Link29.2TransNormal-22026-09-06
Video Generation Models are General-Purpose Vision Learners29.3GenCeption Generalist-L2026-07-10
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model✓ Link30.3Lotus-2 (zero-shot)2025-11-30
NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors✓ Link30.7NormalCrafter2025-04-15
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction✓ Link32.3Lotus-D (zero-shot)2024-09-26
Video Generative Models as Geometry Learner✓ Link33.0GeoNeXt2026-08-28
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think✓ Link33.4GeoWizard + E2E FT (zero-shot)2024-09-17
Rethinking Inductive Biases for Surface Normal Estimation✓ Link34.9DSINE (zero-shot)2024-03-01
Check out how to contribute new results. Then edit this file on GitLab or GitHub.