We present “3D magician”: TADA! Text to Animatable Digital... Avatars. Given a textual description as input only, our method TADA generates expressive animatable 3D avatars with high-quality geometry and lifelike textures. (1/10)show more

(1/2) 📢📢𝗦𝗰𝗲𝗻𝗲𝗧𝗲𝘅 📢📢 Given scene geometry and text prompt... -> SceneTex generates high-quality textures. Main idea: directly optimize scene texture with gradients from a score-distillation objective with view sampling.show more

Garment3DGen 3D Garment Stylization and Texture Generation We introduce... Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on bothshow more

(1/2) Happy to announce that Text2Tex has been accepted... at #ICCV2023 🎉 Taking a mesh and a text prompt as input, Text2Tex generates high quality textures - it's fully automated and easy to scale to many models! Project: Video:show more

📢🚗✨ Excited to announce InfiniCube, our scalable generative model... for dynamic 3D driving scene generation with high fidelity and controllability! InfiniCube generates very large-scale (300m×400m ~ 100,000m^2), dynamic 3D driving scenes given HD maps, 3D bounding boxes, and text prompts as controls. Website: Props to Yifan Lu for leading this project!!!! [1/N]show more

As we move more and more into 3D, texturing... 3D assets will be essential ☝️ Repainting 3D Assets is a new AI method that can take any 3D asset and paint it with a given text prompt. The results, while low-resolution, are pretty impressive.show more

After 4 months in beta Avaturn avatars with ARKit... blendshapes support released! We are live on Product Hunt! Support us at We also added TONS of new Features (see detailed description in the comment below) Shoutout to Chris Messina for hunting us, to Three.js for awesome dev tool, and a huge thank you to our phenomenal community of game developers & 3D creators - you make this journey worthwhile! #ProductHunt #3D #Avatars #Metaverse #GameDevshow more

Today, we're shipping MLX support for TADA, our open-source... text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.show more

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic... Gaussians paper page: Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.show more

📢GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans📢... We present a novel method to reconstruct hair strands from colorless 3D scans by extracting orientation cues directly from the mesh surface geometry by finding local characteristic lines and from shaded renderings using a neural 2D line detector. We enhance the reconstruction with a diffusion prior trained on synthetic hair data and adapted to each scan using a tailored text prompt, allowing us to recover both simple and complex hairstyles without relying on color input. To support further research, we also introduce Strands400, the largest publicly available dataset of 3D hair strand reconstructions from real-world scans of 400 different people, featuring complicated hairstyles, such as ponytails and buns. 🌍 📷 Great work by Rachmadio Noval L. Artem Sevastopolsky Egor Zakharov @ness_prisshow more

Here is a preview of the new bang options... for our 3D customizable vtuber model! ✨ Not everyone can afford a high end 1:1 3D vtuber model. Which is why my sister and I are working so hard to provide a customizable 3D vtuber avatar with the same level of quality and tech!🩷show more

(1/2) MonoNPHM will be presented as a #CVPR2024 Highlight!... Our Neural Parametric Head Model parametrizes both geometry and appearance. With the learned model, we can then 3D reconstruct and track human heads from images or videos.show more

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A... new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.show more

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from... In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.show more

How to generate 3D miniature city models and animate... them using Kling AI? This visual effect can be created with Kling O1, and then rotated in 3D using Image to Video. The image prompt used for generation is as follows: Present a clear, 45° top-down isometric miniature 3D cartoon scene of New York featuring its most iconic landmarks and architectural elements. Use soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadows. Integrate the current weather conditions directly into the city environment to create an immersive atmospheric mood.Use a clean, minimalistic composition with a soft, solid-colored background. At the top-center, place the title "New York" in large bold text in white. You can create different effects by changing the city name according to your needs.show more

Break-A-Scene: Extracting Multiple Concepts from a Single Image introduce... the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method paper page:show more

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates... task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.show more

Our focus is to bring immense value to our... members. We’re going to be releasing many exciting products for OCMs. We believe that Bitcoin will be home to the highest value digital assets and we’re excited to be building there for all OCMs. Our newest collection coming to Bitcoin, OCM Dimensions, will be a first of its kind digital asset collection. Dimensions is high-end, 3D generative art. Our collectors will access the most high quality and groundbreaking digital assets, and only available through OCM. After Dimensions, we'll release another collection for our holders. This collection will be designed by renowned artist Alexis André, creator of Friendship Bracelets. Now is an amazing time to become a member of our Wealthy Digital Nation. Join our Discord for more details.show more

Visual Preset #01 Ink-Brush Cinematic 3D: A high-end cinematic... 3D style where expressive ink-brush effects become the primary visual language for fast-paced anime action. Lately I've noticed that I've been experimenting with different visual presets across my videos and I'd like to explore that direction even further. Going forward, I'll be sharing some of these style experiments. The video below was generated using only a character sheet, a single-line scene description and the visual preset shown below. Created with Seedance 2.0 on Try ArtCraft Seedance 2.0 Prompt: A mesmerizing display of @[character]'s masterful swordsmanship. High-end cinematic 3D realism fused with expressive ink-brush action. High-sakuga anime choreography, sweeping sumi-e brush strokes, flowing ink splashes, dynamic calligraphic energy and graphic black ink trails define every movement. Extreme perspective, dramatic foreshortening, cinematic tracking shots, volumetric lighting, heavy atmospheric haze and explosive ink bursts replace conventional visual effects, while realistic materials and feature-film rendering preserve depth, weight and scale.show more