zhyever
Will train with Depth Anything V2？
Second this... I couldn't get PatchFusion running locally, but I also request Depth Anything v2 support
Hi guys, I think the PatchFusion is not the best solution for the hr depth estimation. We now have PatchRefiner with better performance. I will try to support Depth Anything v2 in PatchRefiner.
One more thing to be noticed: The PatchFusion uses the Swin Transformer block which is hard to be converted to onnx model. So it might be bad. In PatchRefiner, we drop it off and the model has even better performance.
Hi guys, I think the PatchFusion is not the best solution for the hr depth estimation. We now have PatchRefiner with better performance. I will try to support Depth Anything v2 in PatchRefiner.
One more thing to be noticed: The PatchFusion uses the Swin Transformer block which is hard to be converted to onnx model. So it might be bad. In PatchRefiner, we drop it off and the model has even better performance.
Thank you for your responses. I'm interested to see results from PatchRefiner (and using Depth-Anything v2 along with whatever else may produce good results). I could never get PatchFusion running on Windows, so I hope the Windows install will be much easier with PatchRefiner. Thank you for your work.
I would also like either PatchFusion or PatchRefiner support Depth Anything V2. Even better would be to directly support the Distill Any Depth. I couldnt run PatchRefiner succesfully but PatchFusion was doing a great job. I only miss the extra sharpness Distill Any depth is offering (and inference time).
