Search AI Products and News

3DV-TON (Textured 3D-Guided Consistent Video Try-on via Diffusion Models) is an innovative technology that delivers a realistic video try-on experience with texture 3D guidance using diffusion models. According to AIbase, 3DV-TON leverages advanced 3D geometry and texture modeling combined with video diffusion models to ensure consistency and realism of clothing in dynamic videos, offering significant potential for e-commerce, fashion, and virtual reality applications.

The official release of Tencent HunYuan 3D generative model version 2.5 marks a significant leap into the ultra-high-definition era of 3D generation technology. This upgrade not only achieves a qualitative leap in modeling precision but also provides users with a more efficient and convenient creative experience, further lowering the barrier to entry for 3D content creation.

Tencent announced the official unveiling of Hunyuan 3D AI Engine 2.5 tomorrow, further revolutionizing AI-powered 3D content creation. According to AIbase, as an upgrade to Hunyuan 3D 2.0, version 2.5 is expected to achieve significant breakthroughs in geometry generation, texture synthesis, and generation speed, providing more efficient solutions for game development, virtual reality, and creative design. Tencent's official announcement has generated significant anticipation among global developers and creators; further details will be...

Amap announced the launch of its HumanRig technology and the open-sourcing of the industry's first large-scale dataset specifically designed for 3D humanoid character rigging. This technology aims to reduce the cost of character animation production and drive the animation industry towards greater efficiency and automation. It serves as a key infrastructure for Amap in building immersive navigation experiences.

Blender-MCP (Model Context Protocol) has been officially open-sourced, enabling seamless integration of Anthropic's Claude AI with Blender. This breakthrough allows users to create complex 3D scenes using natural language prompts. According to AIbase, the tool allows users to generate sophisticated 3D models with text descriptions alone, such as a scene depicting a low-poly dragon guarding treasure, significantly lowering the technical barrier to entry for 3D modeling. Blender-MCP

404-GEN is pioneering a new era in digital content creation by becoming the first decentralized 3D model generation platform integrated with Unity. This integration empowers creators with seamless access to innovative tools, fostering a more democratic and accessible content creation landscape.

In the field of artificial intelligence, 3D vision and spatial understanding are becoming crucial for advancements in embodied AI, autonomous navigation, and virtual reality applications. In March 2025, Hangzhou Qunhe Technology announced the open-sourcing of its self-developed 3D vision large language model, SpatialLM, at the GTC2025 global conference, generating significant industry interest. This model, with its powerful spatial cognition capabilities and cost-effective data processing, offers revolutionary breakthroughs for robot training, architectural design, and AR/VR applications. AIbase is based on the latest information...

Oxford-based startup Lumai, a key player in AI infrastructure, has announced securing over $10 million in funding. The round was led by deep tech investor Constructor Capital, with participation from IP Group, Ventures, Journey Ventures, LIFTT, Qubits Ventures, State Farm Ventures, and TIS.

Researchers in China have unveiled the world's first three-dimensional atlas of a brain-computer interface at the micrometer scale. This groundbreaking achievement significantly improves the safety and precision of brain surgery involving BCIs.

A research team within Alibaba Group recently unveiled TaoAvatar, a groundbreaking technology that creates photorealistic, full-body, talking 3D virtual avatars. Designed for augmented reality (AR) applications, TaoAvatar aims to revolutionize user interaction by providing lifelike, expressive digital personas capable of hearing, speaking, and exhibiting natural movements and expressions. This technology promises to break down the barriers between dimensions, enabling users to interact with vivid, realistic representations of themselves within AR environments.

Recently, an innovative technology named LHM (Large-scale Human Model for Animation) has achieved a significant breakthrough in the field of 3D human body reconstruction, bringing new development directions and application prospects to the field. Reconstructing animatable 3D human bodies from a single image has been a highly challenging task, plagued by ambiguities in geometry, appearance, and deformation separation. Current state-of-the-art research mostly focuses on static human modeling, and these methods often rely on synthetic 3D scans for training, which greatly limits their applications in...

Roblox recently released Cube, a 3D intelligent base model, marking a significant advancement for game developers who can now leverage the power of artificial intelligence in designing game assets. Roblox has always encouraged users to create their own games, items, and clothing, and now this process has become simpler and more efficient. Cube aims to provide developers with a powerful tool capable of generating various in-game experiences. Whether it's 3D objects, scene design, character modeling, or programming scripts, Cube...

Hangzhou-based tech company, Qunhe Technology, has again garnered industry attention for its open-sourced spatial understanding model, SpatialLM, which was acknowledged by Google in a recent research paper. This model's innovation lies in its ability to enable robots to understand the geometrical relationships of the physical world through ordinary videos, marking a significant breakthrough in robot training. SpatialLM's core function is to convert videos captured by a phone into three-dimensional spatial layout information. Users simply need to record their home layout using their phone, and SpatialLM will...

Tencent HunYuan recently announced the launch of five new open-source 3D generative models. Built upon Hunyuan3D-2.0, these models boast faster generation speeds, richer details, and more realistic material expression. Simultaneously, Tencent's self-developed 3D AI creation engine has been upgraded, adding features such as multi-view input, intelligent model simplification, and full format compatibility. It is now fully open to C-end users. Among these new models, the Turbo series maintains high precision and quality while optimizing the geometric generation model...