Game-ready Medieval Weapons Pack now available. Clean topology. Optimized. Engine-ready. Perfect for fantasy RPGs and indie devs. Available now at #gamedev# #indiedev# #3Dmodeling# #Unity# #UnrealEngine# #Godot# #RPG# #GameAssets# #IndieGameDev# #3DAssets#

Hy 3D WorldClaw is out🤯 An agentic workflow that turns a text prompt into a large scale 3D open world. Every scene is freely explorable🌻, built from editable, game-ready 3D assets with real geometry and textures. actual meshes, not video or splats. Project page 👉

🧊 Turning one image into 3D used to force a choice: "accurate on the visible surface but no backside" or "complete but misaligned with the input." World Tracing stacks 3D points per pixel into layers, capturing visible and hidden surfaces at once. Title: World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible URL: 🔍 Overview World Tracing represents geometry as an ordered stack of L camera-space 3D points per pixel. Layer 0 is the visible surface, deeper layers record front-to-back intersections with surfaces hidden behind the foreground, unifying faithful reconstruction and generative completion as one layered problem. ❓ Challenges Solved Image-to-3D carried a fundamental trade-off. ・Depth estimators are pixel-accurate but stop at the visible surface ・Generative 3D models are complete but work in canonical frames, so they misalign with the input World Tracing frames this as faithful generation: accurately reconstruct the visible surface while plausibly generating the invisible. 💡 Methodology & Proposed Approach At its core is WT-DiT, a 1.7B-parameter diffusion transformer. ・Three-way factorized attention (layer-wise, ray-wise, global) preserves depth ordering and front-to-back coherence ・A mixed noise schedule handles the asymmetry between layer 0 (image-constrained, reconstruction-like) and deeper, generative layers by varying noise per layer ・Mix-training lets multilayer (3D assets) and single-layer (RGBD photos) supervision train together 🎯 Use Cases ・Text-driven 3D scene editing (training-free closed-form compositing thanks to pixel alignment) ・Geometry-conditioned novel-view video synthesis using complete hidden geometry as memory ・A TRELLIS hybrid that yields faithful meshes which reproject correctly to the input 📊 Experimental Results It outperforms prior work on object, scene, and dynamic benchmarks. ・Object visible-depth MAE 0.0149 (VGGT 0.0257) ・Complete-shape F-score@0.05 0.549 (TRELLIS 0.204) ・Scene MAE 0.0102, and best dynamic-clip Chamfer L2 at 0.0105 #3DGeneration# #ComputerVision#

New early details about PlayStation 6 have emerged from job listings and reports via MP1st >Sony is developing high-quality AAA 2D and 3D assets for both the current PS5 and the next-gen PS6 console. This suggests some titles could launch with cross-gen support, similar to the transition from PS4 to PS5. >The company is also building out next-gen social apps, along with improved video streaming and multitasking features. >Sony is partnering with an external studio on a new immersive third-person horror game, the project is being built on Unreal Engine 5 and features shooting mechanics, motion performance capture, and a player progression system. >Additional work is focused on upgrading cloud streaming infrastructure for faster performance and advancing machine learning and AI technologies to enhance graphics and real-time visuals. All of this remains very early-stage information pulled from public development postings.

⚡️BREAKING: ByteDance wants Seedance 2.5 to become part of the professional video production stack. ByteDance’s Jimeng AI has rolled out new tools built around Seedance 2.5, including Maya and Blender plugins. The update connects 3D assets, green-screen materials and AI video generation into a more production-ready workflow. //Key upgrades include: - Ultra-long generation mode, supporting videos up to 3 minutes - New Smart Edit mode for targeted video edits - Multi-frame editing for finer control beyond single-frame changes - Better integration with professional 3D workflows #AI# #AIVideo# #Seedance# #ByteDance# #JimengAI# #Blender# #Maya#

Hours of manual asset authoring => Down to 1–2 minutes with 1 prompt. SR Platform generates interactive, simulation-ready 3D assets for training robotics, complete with articulated objects and physics. Native support for MuJoCo and NVIDIA Isaac Sim. Coming in July!