I am developing B3D, a minimal software 3D renderer... that supports triangle rasterization with depth buffering and clipping, perspective projection with a configurable FOV, model transformations (translation, rotation, scaling), and camera control.show more

Happy Monday! We just added raycast sensors to mjlab.... They let a robot sample the scene with virtual rays, returning distances and surface geometry. Rays can use orthographic projection for terrain scanning or perspective projection for simulating a depth camera.show more

Quick rendering math lesson (common trap): FoV in Unreal... Engine isn't interpolated correctly when blending between two cameras The current code does: FoV = lerp(FoVA, FoVB, Weight) however, that's not how you interpolate FoV! To be "perceptually" linear and also correct under aspect ratio scaling, FoV needs to be lerped in tangent space: FoV = atan(lerp(tan(FoVA*0.5), tan(FoVB*0.5), Weight)) * 2 First video showcasing the problem. Blending between a 32:9 camera with 98.21° FoV and a 16:9 camera with 60° FoV. Viewport is 32:9. Due to FoV scaling being Hor+ by default in UE, at 32:9 they should look identical. But during blends, they don't (the FoV isn't stable)! The relationship between FoV and aspect ratio isn’t linear, because FoV is angular In practice, it also means camera interps aren't as smooth as they could be, second video shows that. PR to fix the problem: hopefully it gets merged!show more

I am blown away 🤯. Check this out! CameraCtrl... II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.show more

Art test I did a while back for a... mobile game studio. I don't think it fits my portfolio but I still had fun with it. Was given a brief and a style board and then had to come up with a design myself and model it out. #gameart #blender #b3d #SubstancePainter #3dart #3D #Stylizedshow more

"I'm developing a Romance Roguelite JRPG with deep social... links and TRPG elements." I also do English translation. I also create my own opening animations. #ScreenshotSaturdayshow more

A real-time AI motion capture model with 1B parameters.... Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.show more

I ♥️clipping legwear to the leg & moving it... left/right for that "3D" effect but I hate the lack of perspective. With deformers I managed to move the fishnet around the leg AND have a "Wrap" effect! See the fishnet get tight as it turns around the leg edge? :3 #Live2d #vtubershow more

.Javed Sterritt reimagined classic Sonic in 3D with a... Looney Tunes-style animation and attitude in Blender 🔶, drawing inspiration from a '90s commercial. Get the model and rig for free: #b3d #blender3d #blender #3danimation #SonicTheHedgehogshow more

Depth Anything V2 is a total beast for real-time... 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).show more

Finished 3d Character Comm for ahlyess ! This is... of Zalgo Hellium, I had a fun time working with you and on this model! Thank you so much! (Will spoiler anything too up close!) Created with Zbrush, Blender, Marmoset toolbag, And substance painter(🧵) #themirrorbetweenwalls #b3dshow more

Went in with high expectations for Mahavatar Narsimha. I... already knew the story from my nani, so I was excited for the visual experience. But the animation felt too flat & illustrative, and 3D depth was so minimal that the glasses felt pointless.show more

If I’d known as a kid that one day,... I’d be able to design and animate something like this and 3D print it, all in an afternoon using free software… well I probably wouldn’t have cared but I think it’s cool now! #b3dshow more

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited):... – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.show more

I had an early access to GPT-6 Astra and... I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.show more

Wonderland: Navigating 3D Scenes from a Single Image Contributions:... • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.show more

🚨 I uploaded a random Pepsi logo... and 5... minutes later it was hanging from my bike. No CAD. No 3D skills. No complicated software. I found a tool called Hi3D that turns any 2D image into a printable 3D model instantly. What I made next got progressively more ridiculous 🧵show more

Playing around with World Labs' 3D generator and combining... it with Runway vid2vid to blend myself and the background better. Although it's only a side perspective, you can tell it doesn't have that static image feel because of how the 3D environment is moving.show more