Gate News message, April 23 — ByteDance’s Seed team released Seed3D 2.0, a text-to-3D model that generates textured 3D assets from a single image. The upgrade focuses on geometric precision and material realism, with the API now available on Volcano Ark.
Geometric generation employs a Coarse-to-Fine two-stage strategy: a large-parameter DiT model first establishes coarse-grained topology, then recovers sharp edges and fine surfaces. Material generation uses a Mixture of Experts (MoE) architecture to enhance high-resolution details, incorporating Vision Language Model (VLM) priors to improve material decomposition stability under unknown lighting conditions, outputting complete PBR maps compatible with standard rendering pipelines.
Sixty evaluators with 3D modeling experience conducted blind comparisons across approximately 200 test cases, comparing Seed3D 2.0 against Hunyuan3D-2.5/3.1, Tripo 3.0, Rodin Gen2, HiTem v2.0, and the previous Seed3D 1.0. Geometric generation preference rates ranged from 65.1% to 98.3%, while textured 3D asset preference rates exceeded 69% across all comparisons.
For downstream applications, Seed3D 2.0 can decompose 3D assets into independent components with joint information, outputting URDF format compatible with Isaac Sim and other simulation engines for dynamic interaction scenarios like robotic grasping. At the scene level, it supports text, multi-view image, or video input, combining multiple assets to generate complete scenes.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
Worxphere Rebrands JobKorea With AI-Powered Hiring Tools
Gate News message, April 26 — South Korean HR platform Worxphere has rebranded JobKorea as it transitions from traditional online job boards to AI-driven hiring solutions. The company is consolidating services including JobKorea and Albamon into a unified platform covering permanent employment,
GateNews13h ago
Olenox Announces Merge With CS Digital to Develop Low Cost, Off-Grid Bitcoin Mining Opportunities
The two companies would agree to merge, with CS Digital receiving $55 million in an all-share transaction, to combine Olenox’s energy expertise with CS Digital’s expertise in bitcoin mining. The combined company would seek to develop off-grid mining and AI data center initiatives close to
Coinpedia14h ago
ComfyUI Raises $30M at $500M Valuation in Craft Ventures-Led Round
Gate News message, April 25 — ComfyUI, an AI creator tools startup, has raised $30 million at a $500 million valuation in a funding round led by Craft Ventures. Pace Capital, Chemistry, and TruArrow also participated in the investment, following a $19 million Series A round in late 2024 backed by Ch
GateNews04-25 02:51
XChat Launches on App Store with End-to-End Encryption and Grok Integration
Gate News message, April 25 — XChat, the standalone messaging app from X (formerly Twitter), officially launched on Apple's App Store on April 25. The app is now available for download and use on iOS, with the Android version coming soon.
XChat allows users to log in directly with their X account,
GateNews04-25 02:00
DeepSeek V4-Flash goes live on Ollama Cloud, US-hosted: Claude Code, OpenClaw one-click integration
Ollama Cloud has launched DeepSeek V4-Flash, with inference hosted on U.S. servers, providing three sets of one-click commands to connect Claude Code, OpenClaw, and Hermes. V4-Flash/V4-Pro use a MoE architecture, with native support for 1M context, and reduce costs with Token-wise compression + DSA sparse attention. In a 1M scenario, token FLOPs per token drop by 27%, and KV cache drops by 10%. API-compatible with OpenAI ChatCompletions and Anthropic, making it easy to switch between multiple workflows and lowering costs and data-sovereignty risk.
ChainNewsAbmedia04-24 10:45
