Monocular depth estimation remains challenging as recent foundation models, such as Depth Anything V2 (DA-V2), struggle with real-world images that are far from the training distribution.
We introduce Re-Depth Anything, a test-time self-supervision framework that bridges this domain gap by fusing DA-V2 with the powerful priors of large-scale 2D diffusion models. Our method performs label-free refinement directly on the input image by re-lighting predicted depth maps and augmenting the input. This re-synthesis method replaces classical photometric reconstruction by leveraging shape from shading (SfS) cues in a new, generative context with Score Distillation Sampling (SDS). To prevent optimization collapse, our framework employs a targeted optimization strategy: rather than optimizing depth directly or fine-tuning the full model, we freeze the encoder and only update intermediate embeddings while also fine-tuning the decoder.
Across diverse benchmarks, Re-Depth Anything yields substantial gains in depth accuracy and realism over the DA-V2, showcasing new avenues for self-supervision by augmenting geometric reasoning.
Our main contribution is the re-lighting module that randomizes light conditions and shades the estimated geometry on the input. Notably, the re-lighting does not need to look physically accurate as we are only augmenting not photometrically reconstructing the image.
Key is also the SDS optimization of embeddings and decoder, while leaving the encoder frozen.
Comparison with DA-V2 across datasets. Relative error reduction of Ours over DA-V2 is shown in the last row of each dataset.
Our work builds on top of amazing papers and codebases. Please check out
Depth Anything V2 a SOTA monocular depth estimator.
threestudio a unified framework for 3D content creation from text prompts, single images, and few-shot images, by lifting 2D text-to-image generation models.
Hugging Face a platform that provides libraries for many machine learning tasks like text generation, image generation, and many more.
@article{bhattarai2025redepth,
title={Re-Depth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting},
author={Ananta R. Bhattarai and Helge Rhodin},
journal={ArXiv},
year={2025},
volume={abs/2512.17908}
}