Supervised learning has held 3D Vision back for too long.
Meet RayZer — a self-supervised 3D model trained with zero 3D labels:
❌ No supervision of camera & geometry
✅ Just RGB images
And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy)
🌐 Project: https://t.co/YpHJIu0tfs
(1/4)
[NeurIPS 2025] Pixel-Perfect Depth
https://t.co/PJwnvcDPD9
This work presents Pixel-Perfect Depth, a monocular depth estimation model with pixel-space diffusion transformers. Compared to existing discriminative and generative models, its estimated depth maps can produce high-quality, flying-pixel-free point clouds.
Happy to share that our paper GR2R got accepted in @CVPR 2025! 🥳🥳
In this paper, we generalized the recorruption framework for self-supervised image denoising on natural exponential family distributions
arxiv: https://t.co/R68Pm6ZHBD
code: https://t.co/W29cjTiZGB
I’m excited to share our pre-print of "Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise", in collaboration with @jorgebaccaq and @TachellaJulian.
@jorgebaccaq@TachellaJulian This paper proposed a strategy to address noisy inverse problems in self-supervised learning scenarios when the images are corrupted by noise from the natural exponential family, (i.e., Gaussian, Poisson, Gamma).
arxiv: https://t.co/R68Pm6ZHBD
code: https://t.co/W29cjTiZGB
I’m excited to share our pre-print of "Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise", in collaboration with @jorgebaccaq and @TachellaJulian.
📢 Check out our latest at #ICASSP2024! 🎉 Explore "Deep Plug-and-Play Algorithm for Unsaturated Imaging" where we combine model-based optimization & deep priors, opening new HDR image reconstruction methods from a single capture! Take a look! 🌟
🤓In 2017, Google researchers introduced the Transformer in "Attention is all you need", which took AI by storm.
5 startups were born: @AdeptAILabs (🏦 @airstreet), Inceptive, @NEARProtocol, @CohereAI, CharacterAI.
Only 1/8 authors remain @GoogleAI, another is at @OpenAI.
😉