Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks – Takara TLDR

DeepSeek may be about to shake up the AI world again – what we know

Qwen3-Max-Preview Launched, Officially Claimed to be the Most Powerful Language Model in the Tongyi Qianwen Series_model_and_that

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

From Editor to Dense Geometry Estimator – Takara TLDR

By Advanced AI EditorSeptember 5, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Leveraging visual priors from pre-trained text-to-image (T2I) generative
models has shown success in dense prediction. However, dense prediction is
inherently an image-to-image task, suggesting that image editing models, rather
than T2I generative models, may be a more suitable foundation for fine-tuning.
Motivated by this, we conduct a systematic analysis of the fine-tuning
behaviors of both editors and generators for dense geometry estimation. Our
findings show that editing models possess inherent structural priors, which
enable them to converge more stably by “refining” their innate features, and
ultimately achieve higher performance than their generative counterparts.
Based on these findings, we introduce \textbf{FE2E}, a framework that
pioneeringly adapts an advanced editing model based on Diffusion Transformer
(DiT) architecture for dense geometry prediction. Specifically, to tailor the
editor for this deterministic task, we reformulate the editor’s original flow
matching loss into the “consistent velocity” training objective. And we use
logarithmic quantization to resolve the precision conflict between the editor’s
native BFloat16 format and the high precision demand of our tasks.
Additionally, we leverage the DiT’s global attention for a cost-free joint
estimation of depth and normals in a single forward pass, enabling their
supervisory signals to mutually enhance each other.
Without scaling up the training data, FE2E achieves impressive performance
improvements in zero-shot monocular depth and normal estimation across multiple
datasets. Notably, it achieves over 35\% performance gains on the ETH3D dataset
and outperforms the DepthAnything series, which is trained on 100$\times$ data.
The project page can be accessed \href{https://amap-ml.github.io/FE2E/}{here}.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleMeta Code Llama AI tool for coding officially launches
Next Article OpenAI reorganizes research team behind ChatGPT’s personality
Advanced AI Editor
  • Website

Related Posts

DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks – Takara TLDR

September 6, 2025

Transition Models: Rethinking the Generative Learning Objective – Takara TLDR

September 5, 2025

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings – Takara TLDR

September 5, 2025

Comments are closed.

Latest Posts

Basquiats Linked to 1MDB Scandal Auctioned by US Government

US Ambassador to UK Fills Residence with Impressionist Masters

New Code of Ethics Implores UK Museums to End Fossil Fuel Sponsorships

Morning Links for September 5, 2025

Latest Posts

DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks – Takara TLDR

September 6, 2025

DeepSeek may be about to shake up the AI world again – what we know

September 6, 2025

Qwen3-Max-Preview Launched, Officially Claimed to be the Most Powerful Language Model in the Tongyi Qianwen Series_model_and_that

September 6, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks – Takara TLDR
  • DeepSeek may be about to shake up the AI world again – what we know
  • Qwen3-Max-Preview Launched, Officially Claimed to be the Most Powerful Language Model in the Tongyi Qianwen Series_model_and_that
  • OpenAI reorganizes research team behind ChatGPT’s personality
  • From Editor to Dense Geometry Estimator – Takara TLDR

Recent Comments

  1. ChesterSponi on Marc Raibert: Boston Dynamics and the Future of Robotics | Lex Fridman Podcast #412
  2. Jeffreyorics on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. ChesterSponi on Study: AI-Powered Research Prowess Now Outstrips Human Experts, Raising Bioweapon Risks
  4. 스포츠 픽 on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. Spravkiosh on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.