✨Depth Anything 3: Recovering the Visual Space from Any Views

📝 Summary:
Depth Anything 3 DA3 predicts spatially consistent geometry from any visual inputs, even without known camera poses. It uses a plain transformer backbone and a singular depth-ray prediction target. DA3 achieves new state-of-the-art results on a visual geometry benchmark, outperforming previous mo...

🔹 Publication Date: Published on Nov 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10647
• PDF: https://arxiv.org/pdf/2511.10647

==================================

For more data science resources:
✓ https://t.me/DataScienceT

#ComputerVision #DepthEstimation #AIResearch #Transformers #3DReconstruction

✨Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

📝 Summary:
Transparent objects are hard for perception. This work observes video diffusion models can synthesize transparent phenomena, so they repurpose one. Their DKT model, trained on a new dataset, achieves zero-shot SOTA for depth and normal estimation of transparent objects, proving diffusion knows tr...

🔹 Publication Date: Published on Dec 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.23705
• PDF: https://arxiv.org/pdf/2512.23705
• Project Page: https://daniellli.github.io/projects/DKT/
• Github: https://github.com/Daniellli/DKT

==================================

For more data science resources:
✓ https://t.me/DataScienceT

#ComputerVision #DiffusionModels #DepthEstimation #TransparentObjects #AIResearch