Depth Anything V4 Paper Withdrawn Over False Claims
JFPuget · x · 2026-08-23
Depth Anything V4 has been withdrawn after its central claim was found to be false. The issues extend beyond reproducibility to fundamental inconsistencies within the paper itself. The authors have stated they take scientific integrity seriously and advised against using the paper as reference material.
Background: The paper previously claimed to reconstruct dynamic 4D scenes from monocular video using Riemannian Flow Matching, reducing invalid Gaussians from 12.3% to 0.01%.
More from Models
- Reasonable post-trains Nemotron 3.5 on 3,000 Verus proofs, lifting pass@1 ~30 points to 73.3% — fhuszar · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
- Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16