OpenCodePapers

monocular-depth-estimation-on-scannet-relative-depth-aligned

Depth EstimationMonocular Depth 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.
PaperCodeAbsReldelta1ModelNameReleaseDate
Vision as Unified Multimodal Generation✓ Link0.0390.98SenseNova-Vision2026-07-07
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model✓ Link0.0420.976Lotus-2 (zero-shot)2025-11-30
DINOv3✓ Link0.0440.981DINOv3 + Depth Anything V22025-08-13
AnyDepth: Depth Estimation Made Easy✓ Link0.0540.974AnyDepth ViT-L2026-01-06
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction✓ Link0.0550.965Lotus-D (zero-shot)2024-09-26
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception✓ Link0.0550.979UNIGP2026-06-29
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think✓ Link0.058Marigold + E2E FT (zero-shot)2024-09-17
Video Generative Models as Geometry Learner✓ Link0.0590.958GeoNeXt2026-08-28
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image✓ Link0.0610.953GeoWizard (zero-shot)2024-03-18
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation✓ Link0.0640.951Marigold (ensemble)2023-12-04
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities✓ Link0.0670.957Modus2026-07-28
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks✓ Link0.0720.944DICEPTION (zero-shot)2025-02-24
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think✓ Link0.965Stable Diffusion + E2E FT (zero-shot)2024-09-17
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device✓ Link0.0880.921ZipDepth2026-07-09
Check out how to contribute new results. Then edit this file on GitLab or GitHub.